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

    Neuronpedia

    INDEX
    Explanations

    code snippets in various programming languages

    oai_token-act-pair · gemini-2.0-flash

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kommen
    -0.54
    дитесь
    -0.48
    ASTER
    -0.45
     It
    -0.45
     She
    -0.44
     The
    -0.43
     «
    -0.43
    ropol
    -0.42
     J
    -0.42
    angle
    -0.42
    POSITIVE LOGITS
    Rhestr
    0.97
     فريبيس
    0.93
     незавершена
    0.85
     ویکی‌پدیا
    0.83
    RenderAtEndOf
    0.80
    المناصب
    0.79
     esternos
    0.79
     للمعارف
    0.77
    UnsafeEnabled
    0.75
     يتيمه
    0.75
    Act Density 10.123%

    No Known Activations