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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     further
    -0.07
    okrat
    -0.07
    .Second
    -0.06
     battled
    -0.06
    AlertDialog
    -0.06
     supper
    -0.06
     First
    -0.06
    께
    -0.06
    HttpException
    -0.06
     Router
    -0.06
    POSITIVE LOGITS
     humorous
    0.07
     ре
    0.06
     확실
    0.06
    ätze
    0.06
    :convert
    0.06
     LINE
    0.06
    ")↵↵↵
    0.06
    (usuario
    0.06
    دا
    0.06
    习
    0.06
    Act Density 0.015%

    No Known Activations