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

    Neuronpedia

    INDEX
    Explanations

    millimeters and mm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ive
    3.41
     stade
    3.09
    ి
    3.03
    र
    2.97
     cual
    2.95
    ی
    2.89
     tetap
    2.87
    ра
    2.74
    ни
    2.72
    வ்வளவு
    2.71
    POSITIVE LOGITS
    ب
    3.46
    dni
    3.40
    د
    3.02
    т
    2.86
    ت
    2.84
    tattoo
    2.82
    জ
    2.72
     IME
    2.67
    timetable
    2.66
     fuelled
    2.60
    Act Density 0.013%

    No Known Activations