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

    Neuronpedia

    INDEX
    Explanations

    exercises and stretching

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    腹泻
    -0.08
    找
    -0.07
     رجال
    -0.07
     среди
    -0.07
     flo
    -0.07
    缀
    -0.07
    ử
    -0.07
    宰
    -0.07
     такое
    -0.07
    过了
    -0.07
    POSITIVE LOGITS
    (changes
    0.08
    volução
    0.07
     Sonata
    0.07
    镬
    0.07
    ...'↵
    0.07
    Modern
    0.07
    帖
    0.07
    }`,↵
    0.07
     않
    0.07
    锔
    0.07
    Act Density 0.019%

    No Known Activations