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

    Neuronpedia

    INDEX
    Explanations

    Webpages and links

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reckless
    -0.08
     desap
    -0.08
    .subtract
    -0.08
    Immutable
    -0.08
     rial
    -0.08
     khí
    -0.07
    cutta
    -0.07
    iense
    -0.07
     explode
    -0.07
    谨
    -0.07
    POSITIVE LOGITS
    网页
    0.17
    ：http
    0.15
    网址
    0.15
    访问
    0.15
    網址
    0.14
     localhost
    0.14
     брауз
    0.14
    浏览
    0.14
     веб
    0.13
     HTTPS
    0.13
    Act Density 0.015%

    No Known Activations