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

    Neuronpedia

    INDEX
    Explanations

    degrees or angles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ထဲ
    0.76
     मझ
    0.74
    ochial
    0.71
    ამართ
    0.70
    ழ்க
    0.70
    kjhtml
    0.69
     xổ
    0.68
    zhihu
    0.68
    lia
    0.67
     mannit
    0.67
    POSITIVE LOGITS
     degrees
    4.55
     degree
    4.34
    degree
    4.15
    degrees
    4.09
     Degree
    4.04
    Degree
    4.04
     Degrees
    3.98
    Degrees
    3.71
    °
    3.41
     डिग्री
    3.28
    Act Density 0.173%

    No Known Activations