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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     оригіналу
    -0.70
     kasarigan
    -0.65
    enumii
    -0.63
     >=",
    -0.62
    <bos>
    -0.61
     loob
    -0.59
     colorés
    -0.59
    ywna
    -0.58
    enumi
    -0.57
     seguinte
    -0.57
    POSITIVE LOGITS
    bootstrapcdn
    0.55
    featureID
    0.52
    évaluateur
    0.46
     NSCoder
    0.45
     satel
    0.45
    Personendaten
    0.44
    intracht
    0.43
     melts
    0.42
     melt
    0.42
     kaarangay
    0.41
    Act Density 0.001%

    No Known Activations