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

    Neuronpedia

    INDEX
    Explanations

    discount rate calculation and estimation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    imaging
    0.44
     contando
    0.41
    限于
    0.41
    Scheduling
    0.40
     monastic
    0.40
    诰
    0.40
    舢
    0.39
    Counting
    0.39
     modalidad
    0.39
     স্পষ্টভাবে
    0.38
    POSITIVE LOGITS
     discount
    0.72
     Discount
    0.65
     DISCOUNT
    0.64
     할인
    0.63
     judgement
    0.61
     discounts
    0.61
     personal
    0.60
     subjective
    0.60
    discount
    0.60
    Discount
    0.59
    Act Density 0.002%

    No Known Activations