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

    Neuronpedia

    INDEX
    Explanations

    years and weeks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     День
    0.55
     Hourly
    0.51
    Hourly
    0.51
     الساعه
    0.51
    hourly
    0.50
     السنه
    0.50
     hourly
    0.50
    День
    0.49
    DAY
    0.48
    Hora
    0.48
    POSITIVE LOGITS
     years
    1.37
    years
    1.09
     años
    0.87
     Jahren
    0.80
     سنوات
    0.79
     Years
    0.78
     YEARS
    0.76
     anos
    0.74
     weeks
    0.74
     months
    0.72
    Act Density 0.089%

    No Known Activations