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

    Neuronpedia

    INDEX
    Explanations

    pandas library calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ዶች
    0.78
     reken
    0.77
     plastik
    0.75
     fontos
    0.73
     উৎকৃষ্ট
    0.73
    ispielsweise
    0.73
     magaz
    0.72
    oną
    0.72
    iono
    0.72
    aną
    0.71
    POSITIVE LOGITS
     Tous
    0.73
     sw
    0.73
    sw
    0.71
     Wh
    0.71
     preceding
    0.69
     Swallow
    0.69
     USDT
    0.68
     code
    0.67
     Healthy
    0.66
     associated
    0.65
    Act Density 0.001%

    No Known Activations