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

    Neuronpedia

    INDEX
    Explanations

    quantifying time periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pendant
    0.77
    三次
    0.75
     উপাদান
    0.70
     twice
    0.70
     až
    0.69
     trois
    0.68
    ৫০
    0.68
    रीबन
    0.68
    直到
    0.67
    唋
    0.67
    POSITIVE LOGITS
     day
    2.93
     week
    2.68
     month
    2.58
     days
    2.56
     year
    2.27
    day
    2.24
     Day
    2.22
     weeks
    2.19
    month
    2.16
     DAY
    2.12
    Act Density 0.464%

    No Known Activations