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

    Neuronpedia

    INDEX
    Explanations

    roles ending in -er

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ری
    0.81
    1
    0.68
    تس
    0.67
    ن
    0.64
    لی
    0.64
    ادف
    0.63
    to
    0.62
    ת
    0.62
    过
    0.61
    着
    0.61
    POSITIVE LOGITS
     extraordinaire
    0.69
     নন
    0.51
    lerce
    0.50
     мощности
    0.50
    romatic
    0.49
     unscrupulous
    0.49
    嬪
    0.48
     coloro
    0.48
    iong
    0.48
    gb
    0.47
    Act Density 0.317%

    No Known Activations