When Activation Oracles Learn Not to Read: Concept-Specific Blind Spots in Fine-Tuned Oracles

arXiv:2607.23379 · cs.CL, cs.AI · Submitted 2026-07-25 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-07-25

Updated: 2026-11-05

Terminology

Sources

Related papers