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

    Neuronpedia

    INDEX
    Explanations

    Bypass

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    房车
    -0.08
    [length
    -0.08
    增加值
    -0.07
     SEA
    -0.07
    [MAXN
    -0.07
    -China
    -0.07
    相对来说
    -0.07
    .Framework
    -0.07
    宁县
    -0.07
     fullfile
    -0.07
    POSITIVE LOGITS
    uate
    0.07
    Color
    0.07
    0.07
    edelta
    0.07
    سمع
    0.06
     uncertainty
    0.06
     impression
    0.06
     rectangles
    0.06
    �
    0.06
    Batch
    0.06
    Act Density 0.003%

    No Known Activations