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

    Neuronpedia

    INDEX
    Explanations

    json structure closing curly brace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     行政
    1.57
    ઞ
    1.56
     判断
    1.48
     以及
    1.48
     创建
    1.44
     防
    1.43
     શ્રી
    1.42
     основним
    1.41
     省
    1.41
     setItems
    1.41
    POSITIVE LOGITS
    show
    0.91
    Submitted
    0.90
     vuelve
    0.88
    verg
    0.87
    weil
    0.84
    de
    0.84
    eller
    0.83
    demon
    0.79
    pero
    0.78
    vul
    0.77
    Act Density 0.000%

    No Known Activations