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

    Neuronpedia

    INDEX
    Explanations

    dates and timeframes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     당시
    0.39
     벡터
    0.38
    မ်း
    0.37
    忽略
    0.37
     அளித்த
    0.36
     দান
    0.36
     intelligently
    0.36
    论
    0.35
     primitive
    0.35
    atat
    0.35
    POSITIVE LOGITS
     dates
    0.77
     fecha
    0.75
     timeframe
    0.72
     deadlines
    0.70
     date
    0.70
     December
    0.68
     commenced
    0.68
     сроки
    0.68
     September
    0.67
     дату
    0.67
    Act Density 0.158%

    No Known Activations