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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inaccessible
    -0.07
    CUDA
    -0.07
     Du
    -0.07
     quitting
    -0.07
     UTF
    -0.07
     family
    -0.06
     ZeroConstructor
    -0.06
    ı
    -0.06
    _json
    -0.06
    _VER
    -0.06
    POSITIVE LOGITS
    seven
    0.06
    fbe
    0.06
    oden
    0.06
     Περι
    0.06
    тиров
    0.06
     equalTo
    0.06
     آسی
    0.06
    比较
    0.06
     PLATFORM
    0.05
    xBA
    0.05
    Act Density 0.038%

    No Known Activations