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

    Neuronpedia

    INDEX
    Explanations

    motivation and reminders

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    毁
    -0.08
    .cfg
    -0.08
     arterial
    -0.08
     buses
    -0.08
     Characteristics
    -0.08
    ;,
    -0.08
     Seks
    -0.07
     apet
    -0.07
    特点
    -0.07
    平成
    -0.07
    POSITIVE LOGITS
     symbolism
    0.11
     symbolizes
    0.11
     encouragement
    0.11
     رمز
    0.10
     प्रती
    0.10
     подарок
    0.10
    扫一扫
    0.10
     symbolize
    0.10
     hadiah
    0.10
     symbol
    0.10
    Act Density 0.060%

    No Known Activations