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

    Neuronpedia

    INDEX
    Explanations

    coaching and coaches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Instruments
    0.47
     ✨
    0.42
     spielt
    0.41
     Inflation
    0.41
     exclusion
    0.41
     Waals
    0.39
     instruments
    0.38
     extr
    0.38
    VERNMENT
    0.38
     ಕ
    0.38
    POSITIVE LOGITS
     coaching
    1.82
     coaches
    1.71
     coach
    1.70
     Coaching
    1.61
    coach
    1.57
     COACH
    1.55
    Coach
    1.53
     Coach
    1.52
    教练
    1.50
     Coaches
    1.48
    Act Density 0.002%

    No Known Activations