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

    Neuronpedia

    INDEX
    Explanations

    Four

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Report
    -0.08
    (JNIEnv
    -0.07
     [-
    -0.07
    新闻记者
    -0.07
    NSDictionary
    -0.07
    nect
    -0.06
     CONST
    -0.06
    닌
    -0.06
    //**↵
    -0.06
    frared
    -0.06
    POSITIVE LOGITS
    勾
    0.08
     businesses
    0.07
    HO
    0.07
    making
    0.07
    (mail
    0.07
    館
    0.07
     songs
    0.07
    カード
    0.06
    으로
    0.06
    事
    0.06
    Act Density 0.000%

    No Known Activations