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

    Neuronpedia

    INDEX
    Explanations

    Edge

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alcoholic
    -0.08
     Carol
    -0.08
     Ngọc
    -0.08
     vamos
    -0.08
     Kaiser
    -0.08
    ﹹ
    -0.07
     Tổng
    -0.07
     TAKE
    -0.07
    aiser
    -0.07
    打赢
    -0.07
    POSITIVE LOGITS
    屏蔽
    0.08
    _NEW
    0.07
    结构
    0.07
    $
    0.07
     pathway
    0.07
    .IT
    0.07
     institutions
    0.07
    .xml
    0.07
     regexp
    0.07
     quirky
    0.07
    Act Density 0.002%

    No Known Activations