Correct self-harm residual framing: incidental outcome, not deliberate design (matches Gemma card)

README.md

@@ -50,7 +50,7 @@ Because the neuron mask is **column-level** and orthogonal to the **row-level**
 
 Removal is performed by directional ablation / weight orthogonalization (projecting the offending direction(s) out of the relevant weight matrices), so the edit is **baked into the weights** and requires no inference-time hook.
 
-**Selective removal.** Refusals associated with **self-harm and suicide are deliberately preserved** — the corresponding contrast set is excluded from the directions that are projected out, so the model retains those guardrails. This is a design choice, verified in the validation probe below.
+**Residual self-harm refusals (accepted).** The removal targets the dominant refusal subspace; it does not separately exclude or protect any category. In practice a small residual of refusals remained, concentrated on self-harm and suicide prompts (see Validation). This was an *outcome*, not a *design*: the removal was not constructed to preserve those guardrails. For the intended research use the residual is acceptable, so it was left in place. **Deliberate, category-selective abliteration** — preserving chosen guardrails by construction while removing others — is a promising direction for future work.
 
 ## Validation
 
@@ -62,9 +62,9 @@ The edit was validated for both **refusal removal** and **absence of damage**, s
 | Refusal removal (development target eval) | **0.8125** (three-stage synergy + CNA-from-base) |
 | Incoherence | **0.0** (no degeneration) |
 | Cognitive damage (capability/coherence probe) | **none observed** |
-| Self-harm / suicide guardrails | **retained (by design)** |
+| Residual self-harm/suicide refusals | **~2.5%, soft, concentrated on self-harm (accepted, not by design)** |
 
-The residual ~2.5% of retained refusals are concentrated on the deliberately-preserved self-harm/suicide prompts. We interpret this as a clean, undamaged uncensoring rather than the degenerate "compliance" that blunt refusal-string removal can produce.
+The residual ~2.5% of retained refusals are concentrated on self-harm/suicide prompts — an accepted outcome, not an engineered carve-out. We interpret this as a clean, undamaged uncensoring rather than the degenerate "compliance" that blunt refusal-string removal can produce.
 
 ### EvalKit benchmark sweep (Q4_K_M)
 
@@ -110,7 +110,7 @@ An independent 200-prompt residual-refusal audit (`refusal_bench`, 2026-06-27) w
 | coherence (control) | 30 | 97% | |
 | **selfharm** | 10 | **70%** | 3 soft-refused |
 
-The only residual friction is the **self-harm** category: the model answers genuine support questions but declines lethal-means requests, emitting crisis-resource language instead — the **deliberately retained guardrail** behaving as designed. **Hard-refusal rate is 0.0%** across every category, and the control/coherence prompts are clean.
+The only residual friction is the **self-harm** category: the model answers genuine support questions but declines lethal-means requests, emitting crisis-resource language instead — a residual, unengineered soft-refusal pattern rather than a designed guardrail. **Hard-refusal rate is 0.0%** across every category, and the control/coherence prompts are clean.
 
 ## Intended use
 
@@ -126,7 +126,7 @@ This model must **not** be used to generate content that is illegal, that facili
 ## Responsible use & ethical considerations
 
 - **Dual use is acknowledged openly.** Refusal removal is a well-documented research technique; this release is in that lineage and exists to support research, not to evade accountability.
-- **Removal is selective**, with self-harm and suicide guardrails preserved — a deliberate, responsible-removal stance rather than blanket stripping.
+- **A residual of soft refusals on self-harm content remained** and was accepted rather than forced out. This was incidental, not an engineered carve-out; deliberate, category-selective abliteration is noted as a direction for future work.
 - **You are responsible** for outputs you generate and for complying with the base model's license and applicable law.
 - **Honesty about capability.** The numbers above are from real eval runs on this checkpoint; capability eval is reported as *pending* rather than asserted. If you benchmark this model, decontaminate your evaluation sets — uncensored-model leaderboards are frequently inflated by train/eval leakage.