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

    Neuronpedia

    INDEX
    Explanations

    location

    np_max-act · gemini-2.0-flash

    This neuron detects the phrase “is located in,” i.e. a location‐attribution construction.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _py
    -0.07
     pě
    -0.06
    ambi
    -0.06
    áže
    -0.06
    險
    -0.06
    ówn
    -0.06
    ToJson
    -0.06
    _bin
    -0.06
     �
    -0.06
     Hastings
    -0.06
    POSITIVE LOGITS
     LEFT
    0.07
     crea
    0.06
     approximate
    0.06
     ping
    0.06
     XPath
    0.06
    Martin
    0.06
    谓
    0.06
    ">-->↵
    0.06
    0.06
     obtain
    0.06
    Act Density 0.015%

    No Known Activations