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

    Neuronpedia

    INDEX
    Explanations

    python imports and multiprocessing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ivatives
    0.73
    cele
    0.65
    Paper
    0.65
     berl
    0.65
    ุ
    0.64
     खेलकर
    0.64
    $\
    0.64
     சென்ற
    0.62
    Grade
    0.62
    Columbia
    0.61
    POSITIVE LOGITS
    渀
    0.94
    iprocal
    0.89
    édé
    0.87
    addington
    0.86
    ন্ত্রণ
    0.85
     visage
    0.85
     Gesicht
    0.83
     boobs
    0.83
     EC
    0.83
    țit
    0.82
    Act Density 0.000%

    No Known Activations