Single neurons can steer LLM behavior — echoing a 2007 finding in real brains
HistedLab · x · 2026-10-21
HistedLab highlights the "God neuron" finding in LLMs: stimulating a single neuron can be steered to change model function. They draw a parallel to Brecht & Houweling (2007), who showed stimulating one neuron in the brain can change behavior — while noting brains remain deeply polysemantic and far less clean than LLMs for interpretability work.
More from Research
- Electric Plant Unveils Bombadil, a Foundation Model Trained on 7M Hours of Plant Bioelectric Signals — manosaie · 2026-10-21
- EdgeKernelBench: LLM-Generated Kernels Hit 64.5% Correct but Only 25.5% Fast on Edge Backends — encodelab · 2026-10-21
- MMEnterprise-Bench from KAIST Tests Enterprise Agents on Conflicting, Evolving Multimodal Records — Seohyun Lee · 2026-10-21
- TRACE Organizes Daily Clinical Events into Trajectories for Inpatient Risk Prediction — Minjun Kim · 2026-10-21
- NTU and Alibaba's FocusGUI: a lightweight adapter filters multimodal evidence to stop GUI agent error compounding — NanyangTechnologicalUniversity · 2026-10-21
- PhysSkin++ learns self-supervised neural skinning fields for real-time physics animation across diverse 3D shapes — Yuanhang Lei · 2026-10-21