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

    Neuronpedia

    INDEX
    Explanations

    normal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    꺳
    -0.07
     cartel
    -0.07
     taxi
    -0.07
    طل
    -0.07
    𑘁
    -0.07
     taxpayer
    -0.07
    杵
    -0.07
    ilst
    -0.07
    seq
    -0.06
    dae
    -0.06
    POSITIVE LOGITS
    ＂
    0.08
    作文
    0.07
     обязательно
    0.07
    왬
    0.07
    绲
    0.07
    执教
    0.07
    خرى
    0.07
    뭥
    0.07
     om
    0.07
    二等奖
    0.06
    Act Density 0.001%

    No Known Activations