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

    Neuronpedia

    INDEX
    Explanations

    Pandas code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    制止
    -0.07
    منتدى
    -0.07
     breakfast
    -0.07
    -sdk
    -0.07
     Sends
    -0.07
    毁灭
    -0.07
     magical
    -0.07
     dẫn
    -0.07
     gaming
    -0.06
     Höhe
    -0.06
    POSITIVE LOGITS
    aram
    0.08
     Antib
    0.07
     columnName
    0.07
    值得关注
    0.07
    .cookies
    0.07
    Cum
    0.07
    �
    0.07
    (tbl
    0.07
    되지
    0.07
     covariance
    0.07
    Act Density 0.015%

    No Known Activations