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

    Neuronpedia

    INDEX
    Explanations

    you followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    整個
    0.56
     становится
    0.54
     становятся
    0.54
     diventa
    0.52
     addirittura
    0.48
     любую
    0.48
     يصير
    0.48
     conseguir
    0.47
    とにかく
    0.47
     самих
    0.47
    POSITIVE LOGITS
     Please
    0.86
     please
    0.79
    Please
    0.73
    您的
    0.70
     your
    0.68
    您
    0.68
    为您
    0.64
     আপনার
    0.62
     Veuillez
    0.62
     Your
    0.59
    Act Density 0.056%

    No Known Activations