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

    Neuronpedia

    INDEX
    Explanations

    worth a visit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    v
    0.82
    \
    0.82
    o
    0.78
    _
    0.78
    ores
    0.69
    pet
    0.69
    vad
    0.68
    f
    0.66
    h
    0.65
    َ
    0.65
    POSITIVE LOGITS
     numai
    0.79
     paragraphe
    0.70
    OUS
    0.66
    ໃນ
    0.64
    .”.
    0.64
    UL
    0.62
     énon
    0.62
     ໃນ
    0.61
    ,”
    0.61
     algoritmo
    0.60
    Act Density 0.003%

    No Known Activations