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

    Neuronpedia

    INDEX
    Explanations

    the concept of request and response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.66
    ’
    0.65
    t
    0.64
    rard
    0.59
    ributions
    0.57
    i
    0.57
    chaften
    0.56
    etiti
    0.54
    iterations
    0.53
    fares
    0.53
    POSITIVE LOGITS
     الفي
    0.65
     Аль
    0.61
    Segundo
    0.60
    北京市
    0.59
     സെക്രട്ടറി
    0.59
    ダイ
    0.59
     Авто
    0.59
    是一名
    0.58
    4
    0.58
     Inicio
    0.57
    Act Density 0.001%

    No Known Activations