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

    Neuronpedia

    INDEX
    Explanations

    sexual content and short lengths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    0.68
    API
    0.68
    របស់
    0.64
    div
    0.63
    PIN
    0.63
    GM
    0.63
    ه‌ی
    0.62
    Needed
    0.62
    subplot
    0.61
    needed
    0.60
    POSITIVE LOGITS
     AND
    1.10
     and
    1.08
     etc
    1.08
     nhưng
    1.08
     و
    1.03
     but
    1.03
    以及
    1.01
     pero
    1.00
     અને
    1.00
     ਅਤੇ
    1.00
    Act Density 0.000%

    No Known Activations