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

    Neuronpedia

    INDEX
    Explanations

    double, dual, half, duplicate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     पत्र
    0.48
    അ
    0.46
    cosystem
    0.45
    各类
    0.44
     ശ്ര
    0.43
    सुम
    0.43
     तमाम
    0.42
    quả
    0.42
    government
    0.41
    כל
    0.41
    POSITIVE LOGITS
     double
    1.24
     doppio
    1.15
     Double
    1.09
    雙
    1.05
     dual
    1.05
    Double
    1.04
    双
    1.04
     two
    1.03
     duality
    1.02
     doubled
    1.01
    Act Density 0.415%

    No Known Activations