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

    Neuronpedia

    INDEX
    Explanations

    .Media

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    拶
    -0.07
    쇼
    -0.06
     Suite
    -0.06
    发展壮大
    -0.06
     contends
    -0.06
     символ
    -0.06
    深知
    -0.06
    文章
    -0.06
     sua
    -0.06
     sóc
    -0.06
    POSITIVE LOGITS
    外交
    0.08
     капит
    0.07
    -master
    0.07
    .NET
    0.07
    啧
    0.07
     украин
    0.07
    Rotation
    0.07
    印象深刻
    0.07
    アウ
    0.07
    plt
    0.07
    Act Density 0.003%

    No Known Activations