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

    Neuronpedia

    INDEX
    Explanations

    titles for sections or items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    p
    0.52
    Ր
    0.50
    oo
    0.49
    lai
    0.48
    it
    0.47
     Stages
    0.47
    ians
    0.46
    tt
    0.46
    র্প
    0.46
    i
    0.45
    POSITIVE LOGITS
    ことができます
    0.60
    (
    0.54
    <
    0.53
    образова
    0.49
    コスト
    0.48
    これで
    0.48
    \
    0.48
    ка
    0.47
    κο
    0.46
    データを
    0.46
    Act Density 0.000%

    No Known Activations