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

    Neuronpedia

    INDEX
    Explanations

    bs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    更重要的
    -0.07
     beyond
    -0.07
    Runner
    -0.07
    Attr
    -0.07
    ="../../../
    -0.07
    迟
    -0.06
    -under
    -0.06
    犯
    -0.06
    roker
    -0.06
    Drawable
    -0.06
    POSITIVE LOGITS
     streamline
    0.08
    լ
    0.08
    专业人士
    0.07
     socialist
    0.07
     dataframe
    0.07
    -instagram
    0.06
    传统的
    0.06
     الجسم
    0.06
     sectional
    0.06
    💄
    0.06
    Act Density 0.006%

    No Known Activations