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

    Neuronpedia

    INDEX
    Explanations

    Swiss quartz movement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Units
    -0.74
     reac
    -0.71
     reż
    -0.69
    bake
    -0.69
    rids
    -0.69
     "
    -0.68
     uint
    -0.65
     Stille
    -0.65
    IVEREF
    -0.65
    スラ
    -0.63
    POSITIVE LOGITS
     movement
    1.38
     winding
    1.31
     automatic
    1.09
    winding
    1.05
    movement
    1.03
    automatic
    1.02
    Movement
    0.94
     MOVEMENT
    0.94
     movements
    0.89
     angin
    0.88
    Act Density 0.009%

    No Known Activations