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

    Neuronpedia

    INDEX
    Explanations

    repetitive nonsensical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lux
    -0.07
     Ky
    -0.07
    ".
    -0.07
     factors
    -0.07
    镪
    -0.07
    月份
    -0.07
     gross
    -0.07
     Pry
    -0.07
     sóc
    -0.07
     Pac
    -0.07
    POSITIVE LOGITS
    删除成功
    0.08
    izioni
    0.07
    —even
    0.07
    atoon
    0.07
    部部长
    0.07
    uncios
    0.07
     мобиль
    0.07
     iw
    0.06
    столь
    0.06
     cüm
    0.06
    Act Density 0.018%

    No Known Activations