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

    Neuronpedia

    INDEX
    Explanations

    triangle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Emperors
    0.43
     शीजान
    0.43
    蒔
    0.41
    㹂
    0.40
    淑
    0.39
     jailed
    0.38
    SUFFIX
    0.38
     Chromecast
    0.38
     Habs
    0.38
    ዠ
    0.38
    POSITIVE LOGITS
     triangle
    4.25
     triangles
    4.00
     Triangle
    3.88
    triangle
    3.83
    Triangle
    3.83
     triangular
    3.72
     треуго
    3.63
    三角形
    3.59
     triángulo
    3.41
     triang
    3.38
    Act Density 0.050%

    No Known Activations