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

    Neuronpedia

    INDEX
    Explanations

    creation and establishment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    htmlspecialchars
    0.82
     doğum
    0.80
    formatted
    0.79
     সন্ব
    0.78
     desarroll
    0.78
    entity
    0.78
    ความ
    0.78
     فونب
    0.77
     vaan
    0.77
     something
    0.77
    POSITIVE LOGITS
     and
    0.87
     or
    0.86
     (
    0.72
     или
    0.70
    and
    0.70
     있고
    0.69
    ंशिक
    0.68
     и
    0.68
    mant
    0.66
    ,
    0.65
    Act Density 0.138%

    No Known Activations