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

    Neuronpedia

    INDEX
    Explanations

    code errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DependencyProperty
    -0.07
    ‏
    -0.06
    dej
    -0.06
    InProgress
    -0.06
     детей
    -0.06
     بنی
    -0.06
     Gim
    -0.06
     Starter
    -0.06
    "],"
    -0.06
     f
    -0.06
    POSITIVE LOGITS
     복
    0.06
     实
    0.06
    FLASH
    0.06
    ump
    0.06
    ưu
    0.06
    COL
    0.06
    Добав
    0.06
     �
    0.06
     guard
    0.06
    ận
    0.06
    Act Density 0.001%

    No Known Activations