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

    Neuronpedia

    INDEX
    Explanations

    completing tasks and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ों
    1.85
    {
    1.84
    東西
    1.79
     saddhim
    1.75
    $("#
    1.71
    ૭
    1.65
    دى
    1.64
    אן
    1.64
    으로는
    1.63
    يريا
    1.56
    POSITIVE LOGITS
    2.19
    ért
    1.92
     complet
    1.69
    ap
    1.66
    фай
    1.62
    ක්ෂ
    1.59
     Tage
    1.55
    р
    1.55
     pregnancies
    1.54
    ána
    1.53
    Act Density 0.180%

    No Known Activations