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

    Neuronpedia

    INDEX
    Explanations

    explicit sexual content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ोल
    0.91
    س
    0.91
     ITO
    0.89
    baiki
    0.88
    larla
    0.86
    स
    0.86
    ado
    0.85
    った
    0.83
    lara
    0.82
    할
    0.82
    POSITIVE LOGITS
     explicit
    1.05
    Explicit
    1.03
     Explicit
    0.99
     explicitly
    0.91
    explicit
    0.91
    顕
    0.80
    明确
    0.68
     ذلك
    0.63
    إ
    0.62
     bewusst
    0.62
    Act Density 0.031%

    No Known Activations