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

    Neuronpedia

    INDEX
    Explanations

    motion detection and analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Shifts
    0.41
     Characters
    0.38
     Move
    0.38
     Annie
    0.38
     Placing
    0.38
    िट
    0.38
     Barron
    0.38
    Annie
    0.37
    urities
    0.37
    auh
    0.37
    POSITIVE LOGITS
     Motion
    0.57
    лок
    0.54
     motion
    0.54
    motion
    0.54
    Motion
    0.50
     MOTION
    0.48
    lessly
    0.47
     sickness
    0.47
    モーション
    0.47
    MOTION
    0.45
    Act Density 0.010%

    No Known Activations