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

    Neuronpedia

    INDEX
    Explanations

    time periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     months
    1.20
     Monate
    1.16
    一个月
    1.11
     Months
    1.08
     meses
    1.06
    Months
    1.00
     weeks
    1.00
     Desember
    0.98
     November
    0.98
    months
    0.97
    POSITIVE LOGITS
     middle
    1.11
     midway
    1.02
    late
    1.00
     around
    1.00
    middle
    0.99
    around
    0.95
     mid
    0.92
    roughly
    0.88
     late
    0.87
    Late
    0.87
    Act Density 0.100%

    No Known Activations