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

    Neuronpedia

    INDEX
    Explanations

    rotation and hand gestures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    褴
    0.78
     graffiti
    0.75
    之路
    0.73
     bụ
    0.72
     econometric
    0.71
     Supervis
    0.69
     Kenney
    0.69
    াণ
    0.69
     граф
    0.69
    мети
    0.68
    POSITIVE LOGITS
     rotation
    1.91
     rotate
    1.89
     rotates
    1.82
     Rotation
    1.78
     rotating
    1.77
    Rotation
    1.75
     Rotate
    1.75
    Rotate
    1.70
     rotated
    1.68
     rotations
    1.62
    Act Density 1.333%

    No Known Activations