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

    Neuronpedia

    INDEX
    Explanations

    exercise advice and routines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Active
    0.57
     सक्रिय
    0.51
     Active
    0.50
    active
    0.47
    Office
    0.46
    Nr
    0.46
     práce
    0.46
     active
    0.45
     актив
    0.43
    Practice
    0.43
    POSITIVE LOGITS
     regime
    0.67
     regimes
    0.63
     regimens
    0.62
     regimen
    0.61
     caution
    0.59
     Regime
    0.51
     routines
    0.51
     régimen
    0.48
     régime
    0.46
     intolerance
    0.46
    Act Density 0.009%

    No Known Activations