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

    Neuronpedia

    INDEX
    Explanations

    the three little pigs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ip
    0.74
    im
    0.70
    ver
    0.66
    ron
    0.65
    lik
    0.64
    it
    0.63
    aton
    0.63
    app
    0.62
    uk
    0.62
    ibal
    0.61
    POSITIVE LOGITS
    TempVal
    0.81
    Aquí
    0.79
     DataType
    0.77
     Aşağı
    0.73
    dataFormat
    0.72
    emptyDict
    0.72
    InsertInt
    0.72
    FieldError
    0.71
    силання
    0.71
     Đặc
    0.71
    Act Density 0.000%

    No Known Activations