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

    Neuronpedia

    INDEX
    Explanations

    fractions and numerical values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    パワ
    0.43
    名稱
    0.41
     выбран
    0.40
    товар
    0.39
    วา
    0.38
     регистра
    0.38
     infot
    0.38
    議論
    0.38
     गुम
    0.38
    मिनी
    0.38
    POSITIVE LOGITS
     ½
    0.66
    frac
    0.57
     ¼
    0.55
     Fraction
    0.53
     fraction
    0.52
     ¾
    0.52
     fractional
    0.52
     Hälfte
    0.52
     Fractions
    0.52
    ⅓
    0.52
    Act Density 0.012%

    No Known Activations