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

    Neuronpedia

    INDEX
    Explanations

    workflow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rq
    -0.09
     comedic
    -0.08
     mož
    -0.08
     compressed
    -0.08
    Compressed
    -0.07
    emand
    -0.07
     prices
    -0.07
     pụrụ
    -0.07
    otiate
    -0.07
     مناسب
    -0.07
    POSITIVE LOGITS
     실행
    0.11
    _execution
    0.10
     execution
    0.09
    _runs
    0.09
    Execution
    0.09
    Executed
    0.08
    执行
    0.08
     выполнение
    0.08
    -containing
    0.08
     yür
    0.08
    Act Density 0.030%

    No Known Activations