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

    Neuronpedia

    INDEX
    Explanations

    code, programming, scripting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ㇁
    0.30
    त्रेयी
    0.29
     منٹو
    0.28
    GAMMA
    0.28
     ہمس
    0.28
    <unused1076>
    0.28
     डायरे
    0.27
     بتساوي
    0.27
    𒃻
    0.27
    鏻
    0.27
    POSITIVE LOGITS
    //
    0.39
    print
    0.38
    if
    0.36
     function
    0.36
    var
    0.36
     //
    0.35
    function
    0.34
    0.34
    for
    0.34
    '
    0.33
    Act Density 0.018%

    No Known Activations