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

    Neuronpedia

    INDEX
    Explanations

    author introductions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -svg
    -0.08
    _Version
    -0.08
    网络
    -0.07
    _Float
    -0.07
    排行榜
    -0.07
    Oper
    -0.07
    anggal
    -0.07
     seeming
    -0.06
    وصف
    -0.06
     Series
    -0.06
    POSITIVE LOGITS
    ढ
    0.07
     mężczyzn
    0.07
     billion
    0.07
    aju
    0.07
    "After
    0.07
    (IM
    0.07
    決め
    0.06
    如有侵权
    0.06
    ﾐ
    0.06
    Bern
    0.06
    Act Density 0.002%

    No Known Activations