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

    Neuronpedia

    INDEX
    Explanations

    reCAPTCHA chapt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fehl
    0.99
    dashed
    0.93
    sher
    0.93
    igheten
    0.91
    𒃻
    0.91
    νά
    0.91
    ovis
    0.91
    क्षिप्त
    0.90
    𒁹
    0.90
    ر
    0.90
    POSITIVE LOGITS
    那就是
    0.85
    ﻥ
    0.77
    ﺩ
    0.76
    что
    0.73
     semigroup
    0.72
     hỏi
    0.72
    ध्यक्ष
    0.72
    儡
    0.71
    ‍♂️
    0.70
     Cent
    0.70
    Act Density 0.002%

    No Known Activations