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

    Neuronpedia

    INDEX
    Explanations

    math expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wanted
    -0.07
    ॉट
    -0.07
     мати
    -0.06
    _program
    -0.06
    ‌د
    -0.06
    _fitness
    -0.06
     Meanwhile
    -0.06
    UrlParser
    -0.06
    sın
    -0.06
    리고
    -0.06
    POSITIVE LOGITS
     жиз
    0.07
     açısından
    0.06
    Kim
    0.06
     Á
    0.06
    minated
    0.06
     dụng
    0.06
     leukemia
    0.06
    喝
    0.06
     diffusion
    0.06
    <IM
    0.06
    Act Density 0.027%

    No Known Activations