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

    Neuronpedia

    INDEX
    Explanations

    checkout

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (task
    -0.07
    淘
    -0.07
     Urg
    -0.07
    lust
    -0.07
     Opens
    -0.07
    逊
    -0.07
    UserService
    -0.07
    .GetService
    -0.06
    密度
    -0.06
    .ascii
    -0.06
    POSITIVE LOGITS
     скоро
    0.08
     رائع
    0.07
    一切都
    0.07
    ADOS
    0.07
    폈
    0.07
    谪
    0.07
    教程
    0.06
     pracę
    0.06
    edy
    0.06
    enko
    0.06
    Act Density 0.002%

    No Known Activations