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

    Neuronpedia

    INDEX
    Explanations

    (A) / (B) / (C) formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.46
    、​
    0.44
    ोहित
    0.42
    determ
    0.42
    "",
    0.41
     واقعات
    0.41
     ちゃ
    0.40
    oš
    0.40
    "],
    0.40
    طار
    0.40
    POSITIVE LOGITS
    %)
    0.61
     ͡
    0.61
    この
    0.56
    In
    0.55
    2
    0.54
    approximately
    0.54
    ۱
    0.53
    ૧
    0.52
    hereinafter
    0.51
     Immediately
    0.50
    Act Density 0.027%

    No Known Activations