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

    Neuronpedia

    INDEX
    Explanations

    addresses

    np_max-act · gemini-2.0-flash

    The neuron responds to place names and other geographic/location tokens (e.g. city names and street-type abbreviations).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Penny
    -0.07
    cidade
    -0.07
     BrowserModule
    -0.07
     divides
    -0.06
    emplace
    -0.06
     crust
    -0.06
     drawings
    -0.06
    َل
    -0.06
     sectarian
    -0.06
    _Window
    -0.06
    POSITIVE LOGITS
     اطلاعات
    0.08
     پي
    0.07
     actual
    0.07
     FString
    0.07
     userProfile
    0.07
    ;")↵
    0.06
     trách
    0.06
     Actual
    0.06
    ihar
    0.06
    ')]↵
    0.06
    Act Density 0.140%

    No Known Activations