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

    Neuronpedia

    INDEX
    Explanations

    closing parenthesis followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    و
    0.79
    u
    0.77
    ش
    0.73
    이
    0.69
    ي
    0.66
    기
    0.64
    ين
    0.61
    на
    0.60
    り
    0.59
    ন
    0.58
    POSITIVE LOGITS
    ।
    0.65
    -
    0.55
     (
    0.52
    。
    0.51
     I
    0.47
    (
    0.47
    cence
    0.46
    cido
    0.44
    entino
    0.43
    punkt
    0.43
    Act Density 0.099%

    No Known Activations