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

    Neuronpedia

    INDEX
    Explanations

    shapes and polygons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trụ
    0.44
    Height
    0.41
    HEIGHT
    0.41
    height
    0.40
    parseLong
    0.39
     cylindrical
    0.38
     getHeight
    0.38
    幅
    0.38
    WIDTH
    0.38
    Dimensions
    0.38
    POSITIVE LOGITS
     polygons
    1.47
     polygon
    1.45
     shapes
    1.44
     Polygon
    1.30
     Shapes
    1.25
    shapes
    1.23
    Shapes
    1.22
    polygon
    1.20
    Polygon
    1.19
     shape
    1.08
    Act Density 0.026%

    No Known Activations