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

    Neuronpedia

    INDEX
    Explanations

    specific details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Și
    1.06
    もら
    1.05
    vasive
    0.97
    </h2>
    0.96
    }{
    0.96
    ер
    0.95
     σε
    0.94
    ことなく
    0.93
    ;
    0.92
     ਸ਼
    0.91
    POSITIVE LOGITS
    ம்
    1.73
    ו
    1.66
    ي
    1.55
    י
    1.55
    м
    1.47
    ک
    1.45
    ’
    1.43
    ro
    1.40
    م
    1.35
    س
    1.35
    Act Density 0.160%

    No Known Activations