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

    Neuronpedia

    INDEX
    Explanations

    probability of occurrence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     improved
    0.52
     improves
    0.49
     increased
    0.48
     увеличения
    0.48
     mejora
    0.47
     cucumbers
    0.47
     еле
    0.46
     increases
    0.46
    多少
    0.46
     aumento
    0.46
    POSITIVE LOGITS
    wheeled
    0.54
    than
    0.52
     склон
    0.49
     kuin
    0.46
     niż
    0.46
    claimer
    0.45
     ciek
    0.45
    मेरा
    0.44
    v
    0.44
     खारिज
    0.43
    Act Density 0.028%

    No Known Activations