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

    Neuronpedia

    INDEX
    Explanations

    predicting future events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     manchmal
    0.95
     parfois
    0.91
     Иногда
    0.89
    有时候
    0.86
     иногда
    0.84
     లేదు
    0.80
    Sometimes
    0.79
     있었다
    0.79
    ettiin
    0.78
    んでいた
    0.77
    POSITIVE LOGITS
     will
    5.77
    will
    5.13
     sẽ
    4.89
     akan
    4.63
     WILL
    4.37
     Will
    4.34
    Will
    4.28
     будет
    4.05
     будут
    3.80
     będzie
    3.78
    Act Density 1.187%

    No Known Activations