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

    Neuronpedia

    INDEX
    Explanations

    angle measurement and orientation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ی
    1.26
     are
    1.18
    s
    1.15
     in
    1.09
    tra
    1.05
    ק
    1.02
    sun
    0.97
    tl
    0.96
    یم
    0.95
    sa
    0.94
    POSITIVE LOGITS
    on
    1.38
    ل
    1.20
     ángulos
    0.98
    小
    0.96
     única
    0.93
    У
    0.92
    "
    0.91
    角度
    0.90
    Дру
    0.89
     millió
    0.88
    Act Density 0.109%

    No Known Activations