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

    Neuronpedia

    INDEX
    Explanations

    websites and organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ж
    1.87
    a
    1.83
     volna
    1.81
    √
    1.80
    ${
    1.73
    験
    1.70
    ت
    1.69
    er
    1.68
    я
    1.68
     நாட்கள்
    1.67
    POSITIVE LOGITS
    ../../
    1.86
     willen
    1.73
    ../../../
    1.72
     نحن
    1.66
    న
    1.63
    <unused199>
    1.63
    PRNewswire
    1.58
    น
    1.57
     זאת
    1.50
    های
    1.49
    Act Density 0.225%

    No Known Activations