factual

Multimodal Models Have Concept-Specific Neurons

Single neurons in multimodal models can be concept-specific and cross-modal at different abstraction levels—for example, a 'spider neuron' in the original DALL·E was preferentially activated by images of spiders, the word 'spider,' and images of Spider-Man, analogous to the famous 'Jennifer Aniston neuron' findings in human neuroscience.

factualpending

Speaker

Raphael Milliere

Evidence Quote

“these were mixing responsive to concepts across modalities at different levels of abstraction. So one example would be they found a spider neuron”

Source

230 | Raphaël Millière on How Artificial Intelligence Thinks— Sean Carroll's Mindscape
Created: 6/13/2026, 12:19:51 AM

Your notes

Loading notes...