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

    Neuronpedia

    INDEX
    Explanations

    numerical ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝙤
    0.86
    IFIED
    0.81
    abbing
    0.78
     recently
    0.78
     dekat
    0.77
    listing
    0.77
    stopping
    0.77
    謗
    0.76
     ведь
    0.76
    logging
    0.75
    POSITIVE LOGITS
    ^)
    0.88
    匚
    0.77
    NameTo
    0.74
    运算
    0.73
     Berechnung
    0.73
    Calcul
    0.72
     cul
    0.70
    CultureInfo
    0.70
    calcul
    0.69
    ϡ
    0.69
    Act Density 0.136%

    No Known Activations