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

    Neuronpedia

    INDEX
    Explanations

    video

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .WaitFor
    -0.07
    千伏
    -0.07
    _photo
    -0.07
    ragments
    -0.07
     texting
    -0.07
    keywords
    -0.07
     ARTICLE
    -0.07
    的空间
    -0.07
    دة
    -0.07
     pige
    -0.07
    POSITIVE LOGITS
    .Encoding
    0.07
    ｾ
    0.07
     mitigate
    0.07
    培训班
    0.06
     epic
    0.06
    \xb
    0.06
    limit
    0.06
     Flying
    0.06
    ﾋ
    0.06
    ツアー
    0.06
    Act Density 0.219%

    No Known Activations