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

    Neuronpedia

    INDEX
    Explanations

    digits followed by comma or digit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MSFontService
    1.49
    "",
    1.46
    多了
    1.45
    👉
    1.41
    受伤
    1.39
    yssey
    1.37
    αν
    1.36
    ati
    1.35
    ⃣
    1.34
    🥰
    1.32
    POSITIVE LOGITS
    ف
    3.95
    م
    2.45
    د
    2.41
    ب
    2.23
    ح
    2.06
    فون
    1.84
    ق
    1.80
    क
    1.77
    فن
    1.70
    مق
    1.67
    Act Density 0.536%

    No Known Activations