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

    Neuronpedia

    INDEX
    Explanations

    rotation and direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     financières
    0.61
     финансовых
    0.61
     finanzi
    0.59
     مالی
    0.59
     financiera
    0.58
     financière
    0.58
     salaried
    0.57
     المالية
    0.56
     финансо
    0.56
     financement
    0.56
    POSITIVE LOGITS
     orientation
    1.09
     direction
    1.07
     perpendicular
    1.04
     rotation
    1.03
     angular
    1.03
     angle
    1.02
     clockwise
    1.02
     rotated
    1.00
    Direction
    0.98
    方向
    0.98
    Act Density 0.273%

    No Known Activations