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

    Neuronpedia

    INDEX
    Explanations

    stopwatch functionality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     movement
    0.61
     pausing
    0.57
    movement
    0.55
     pauses
    0.52
     paused
    0.52
     pause
    0.51
    MOVEMENT
    0.50
     movimenti
    0.50
     pausa
    0.49
     slowing
    0.47
    POSITIVE LOGITS
     stopwatch
    0.77
     Stopwatch
    0.74
     SW
    0.66
    SW
    0.66
     Sw
    0.64
     स्व
    0.63
     घड़ी
    0.59
    Sw
    0.59
    clock
    0.57
     chronograph
    0.57
    Act Density 0.001%

    No Known Activations