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

    Neuronpedia

    INDEX
    Explanations

    long duration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spending
    0.89
     Spending
    0.81
     Spend
    0.77
     weekday
    0.71
    对
    0.68
     spend
    0.67
     day
    0.67
     $
    0.66
     instantaneous
    0.65
     lives
    0.65
    POSITIVE LOGITS
     longer
    1.06
     læng
    0.97
    longer
    0.96
     quite
    0.95
     dłu
    0.92
     länger
    0.89
    quite
    0.85
    Long
    0.83
     long
    0.79
     Longer
    0.79
    Act Density 0.100%

    No Known Activations