LLM can concept cells as well. Claude artificially amplified neuron responsible for the Golden Gate Bridge, the resulting LLM, called 'Golden Gate Claude', would mention the Golden Gate Bridge bridge when ever it could.
I'm surprised we don't hear more about this (last mention I remember was in terms of suppressing "undesirable" vectors in the name of "alignment"). I'd love to get my hands on a tool that makes it easy to do this on some of the SOTA OSS models.