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

    Neuronpedia

    INDEX
    Explanations

    Code and output

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    집
    -0.07
    络
    -0.07
    punkt
    -0.07
    碣
    -0.07
    督办
    -0.07
    底蕴
    -0.06
    (Size
    -0.06
    Ɣ
    -0.06
    women
    -0.06
     Nguyen
    -0.06
    POSITIVE LOGITS
    udi
    0.07
    .abs
    0.07
    >.↵↵
    0.07
    life
    0.06
    。「
    0.06
    ")))↵
    0.06
    씸
    0.06
     governo
    0.06
    .ops
    0.06
    iva
    0.06
    Act Density 0.135%

    No Known Activations