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

    Neuronpedia

    INDEX
    Explanations

    first day or day 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    I
    0.78
    _
    0.77
    :
    0.72
    ล
    0.69
    "
    0.62
    '
    0.62
    [
    0.61
    -
    0.58
    VersionUID
    0.55
     slander
    0.55
    POSITIVE LOGITS
    as
    0.60
     Aucun
    0.54
     ακόμα
    0.53
    avoir
    0.52
    sores
    0.52
    órios
    0.50
    éticos
    0.50
    vés
    0.49
     Astros
    0.48
    mér
    0.48
    Act Density 0.051%

    No Known Activations