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

    Neuronpedia

    INDEX
    Explanations

    urls, code, and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Onde
    -0.91
    購
    -0.81
     surcharge
    -0.79
    Ƨ
    -0.79
    Contro
    -0.75
    био
    -0.73
    Население
    -0.73
    thode
    -0.73
     capito
    -0.71
     cunt
    -0.71
    POSITIVE LOGITS
     levando
    0.79
    ヮ
    0.78
    +{
    0.73
    拼
    0.72
    .&
    0.71
    川崎
    0.71
    strategia
    0.70
    要做
    0.70
    ิก
    0.69
    イヤー
    0.69
    Act Density 0.024%

    No Known Activations