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

    Neuronpedia

    INDEX
    Explanations

    failure or errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ندير
    0.46
    UNUSED
    0.42
    SpecID
    0.41
    你會
    0.40
     rápid
    0.40
     کھیلیں
    0.40
     دفاتر
    0.40
     맞춰
    0.39
    你会
    0.38
    યર
    0.38
    POSITIVE LOGITS
     failed
    1.16
     unable
    1.12
    failed
    1.03
    Failed
    0.97
     Unable
    0.96
     실패
    0.96
     Failed
    0.95
     gagal
    0.95
    unable
    0.93
    失敗
    0.90
    Act Density 0.056%

    No Known Activations