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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ulado
    -0.07
    楼
    -0.07
     人
    -0.07
     built
    -0.06
     кон
    -0.06
    _through
    -0.06
    옥
    -0.06
     pro
    -0.06
    .two
    -0.06
    &a
    -0.06
    POSITIVE LOGITS
     Possible
    0.07
    ignal
    0.06
    -directed
    0.06
     če
    0.06
     hãy
    0.06
     jeu
    0.06
    -Muslim
    0.06
     Sep
    0.06
     применя
    0.06
    passwd
    0.06
    Act Density 0.088%

    No Known Activations