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

    Neuronpedia

    INDEX
    Explanations

    its

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    айте
    -0.07
    ículos
    -0.07
    说道
    -0.06
    iever
    -0.06
     worldly
    -0.06
    Những
    -0.06
    投
    -0.06
     KL
    -0.06
     uu
    -0.06
    .activity
    -0.06
    POSITIVE LOGITS
     including
    0.06
     XHTML
    0.06
     targetType
    0.06
    =%.
    0.06
     hỗ
    0.06
     зависим
    0.06
     cuckold
    0.06
     μας
    0.06
    /respond
    0.06
     JADX
    0.06
    Act Density 0.038%

    No Known Activations