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

    Neuronpedia

    INDEX
    Explanations

    say "ans" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mắt
    -0.07
     Hend
    -0.07
    рат
    -0.06
    soup
    -0.06
    636
    -0.06
    ?',
    -0.06
    に出
    -0.06
    "]],↵
    -0.06
     布
    -0.06
    ในช
    -0.06
    POSITIVE LOGITS
     Seven
    0.07
     Eight
    0.06
     گرفته
    0.06
    <System
    0.06
    ýval
    0.06
     olur
    0.06
    paralleled
    0.06
     VII
    0.06
    (non
    0.06
    _HC
    0.06
    Act Density 0.025%

    No Known Activations