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

    Neuronpedia

    INDEX
    Explanations

    exercise of power or rights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cker
    0.51
     gallon
    0.50
    。
    0.49
     Items
    0.45
    cknow
    0.44
     alphanumeric
    0.42
     bath
    0.41
     fleur
    0.41
     accusation
    0.41
     (
    0.41
    POSITIVE LOGITS
     exercised
    0.82
     exercise
    0.65
     exercising
    0.65
     упраж
    0.62
     exercício
    0.60
     eserc
    0.59
     Exercise
    0.58
    锻炼
    0.57
     ejercicio
    0.56
     Exerc
    0.55
    Act Density 0.015%

    No Known Activations