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

    Neuronpedia

    INDEX
    Explanations

    geometric shapes and angles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鸨
    0.77
     皮
    0.73
     مدیر
    0.71
    週期
    0.71
    機制
    0.70
     geração
    0.69
    astaan
    0.69
     disc
    0.68
    棄
    0.68
    稦
    0.67
    POSITIVE LOGITS
     angles
    1.49
    Angles
    1.44
    angles
    1.34
     triangles
    1.33
     Angles
    1.26
     ángulos
    1.23
     vertices
    1.19
     triangle
    1.17
    ángulos
    1.16
     âng
    1.14
    Act Density 0.114%

    No Known Activations