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

    Neuronpedia

    INDEX
    Explanations

    United Nations and its bodies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Crohn
    0.68
    t
    0.66
    d
    0.66
     компо
    0.66
     Австра
    0.66
     spéc
    0.64
     дел
    0.64
     оптима
    0.63
     начну
    0.63
    맛집
    0.63
    POSITIVE LOGITS
    ری
    0.82
    UN
    0.72
    א
    0.67
    ان
    0.66
    ש
    0.63
    רי
    0.62
    ط
    0.62
    ON
    0.62
    لی
    0.62
    ’
    0.62
    Act Density 0.015%

    No Known Activations