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

    Neuronpedia

    INDEX
    Explanations

    walk or jog

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    keyPressed
    0.66
    鏃
    0.65
     жет
    0.65
     మ్యాచ్
    0.64
    茈
    0.63
    幔
    0.63
     hypersurfaces
    0.63
     timeLeft
    0.62
     연료
    0.62
     submarines
    0.62
    POSITIVE LOGITS
     walk
    3.99
     walking
    3.88
     walks
    3.87
     Walk
    3.67
     walked
    3.65
    Walk
    3.61
    walk
    3.61
     Walking
    3.57
    Walking
    3.54
    walking
    3.39
    Act Density 0.281%

    No Known Activations