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

    Neuronpedia

    INDEX
    Explanations

    hypothetical scenarios and possibilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সমূহ
    0.52
     მათი
    0.50
    狎
    0.50
     Bhagavato
    0.48
    possibleTypes
    0.47
     Баскетбол
    0.46
     ट्रोल
    0.46
    ോക
    0.46
     المسي
    0.46
    უს
    0.46
    POSITIVE LOGITS
    -
    0.79
    e
    0.64
    in
    0.63
    t
    0.59
    u
    0.58
     (
    0.57
    i
    0.57
    :
    0.55
     &
    0.53
    str
    0.53
    Act Density 0.004%

    No Known Activations