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

    Neuronpedia

    INDEX
    Explanations

    item selection

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of choosing or selecting items (e.g. “select,” “selected,” “choosing,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     tomato
    -0.07
    気
    -0.07
    ariate
    -0.07
    eni
    -0.06
     gravel
    -0.06
     जन
    -0.06
    절
    -0.06
     PV
    -0.06
    ازي
    -0.06
    NES
    -0.06
    POSITIVE LOGITS
     estad
    0.07
    ridor
    0.07
     شهر
    0.07
    _standard
    0.06
    .Syntax
    0.06
     empresa
    0.06
     الأمريكي
    0.06
     Bankası
    0.06
    APIView
    0.06
     نمای
    0.06
    Act Density 0.021%

    No Known Activations