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

    Neuronpedia

    INDEX
    Explanations

    watch movement finishing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🥦
    0.48
    lamydia
    0.44
     puriso
    0.43
    🥕
    0.42
    MORDOR
    0.41
    🍑
    0.41
     వైసీపీ
    0.40
     हाईवे
    0.40
    痢
    0.40
    iflower
    0.39
    POSITIVE LOGITS
     timepiece
    1.81
    時計
    1.78
     clocks
    1.75
     watches
    1.73
     reloj
    1.73
     clock
    1.70
     Watches
    1.69
     wristwatch
    1.67
    腕時計
    1.59
     Clock
    1.58
    Act Density 0.020%

    No Known Activations