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

    Neuronpedia

    INDEX
    Explanations

    ib

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     بسیاری
    -0.07
     Сер
    -0.07
    ким
    -0.07
     NDP
    -0.06
    최고
    -0.06
    остью
    -0.06
    าตรฐาน
    -0.06
    分
    -0.06
    الی
    -0.06
    (fil
    -0.06
    POSITIVE LOGITS
     öğrenc
    0.07
     historic
    0.07
    Directed
    0.06
     kèo
    0.06
    Recently
    0.06
    assuming
    0.06
     operations
    0.06
     pavement
    0.06
     mum
    0.06
    ..↵
    0.06
    Act Density 0.001%

    No Known Activations