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

    Neuronpedia

    INDEX
    Explanations

    questions about tags

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     professionally
    -0.07
     Nationwide
    -0.07
    _E
    -0.07
    Guardar
    -0.07
    也有
    -0.07
    偏离
    -0.07
     Power
    -0.07
    許
    -0.07
     Norm
    -0.07
    _sku
    -0.06
    POSITIVE LOGITS
    鏊
    0.08
    تص
    0.08
    高尔夫
    0.07
    جموع
    0.07
    قيقة
    0.07
    #line
    0.07
     reefs
    0.07
    ongan
    0.07
    สำรวจ
    0.06
     whats
    0.06
    Act Density 0.018%

    No Known Activations