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

    Neuronpedia

    INDEX
    Explanations

    file formats/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quint
    -0.08
     hostility
    -0.08
     peng
    -0.08
    UNA
    -0.07
    itsin
    -0.07
     hostile
    -0.07
     ehrlich
    -0.07
    arily
    -0.07
     kesehatan
    -0.07
     Serum
    -0.07
    POSITIVE LOGITS
    文件
    0.14
     文件
    0.13
     파일
    0.13
     файла
    0.12
     files
    0.12
    파일
    0.12
     файл
    0.11
     فایل
    0.10
    .gz
    0.10
    ファ
    0.10
    Act Density 0.041%

    No Known Activations