Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    architecture

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of tourist‐attraction terms—especially “architecture” and “landmarks.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     robotic
    -0.07
     Serv
    -0.06
     mHandler
    -0.06
     solving
    -0.06
     logging
    -0.06
    .Flow
    -0.06
     filthy
    -0.06
     bots
    -0.06
     pending
    -0.06
     Bowman
    -0.06
    POSITIVE LOGITS
    .ip
    0.07
    ичні
    0.07
    δή
    0.06
     $(
    0.06
     Secrets
    0.06
    OW
    0.06
     ดาว
    0.06
     SHALL
    0.06
    VIEW
    0.06
     《
    0.06
    Act Density 0.009%

    No Known Activations