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

    Neuronpedia

    INDEX
    Explanations

    names after commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    L
    0.93
    G
    0.84
    W
    0.80
    ح
    0.77
    ır
    0.77
    P
    0.77
    Ls
    0.76
    A
    0.75
    ль
    0.75
    ق
    0.73
    POSITIVE LOGITS
    те
    1.03
    ，
    0.88
    。
    0.86
     секрета
    0.86
     rector
    0.83
     afirmó
    0.78
    ，《
    0.78
     aprire
    0.77
    swagen
    0.76
     ofthe
    0.74
    Act Density 0.651%

    No Known Activations