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

    Neuronpedia

    INDEX
    Explanations

    annual periods and variation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     하루
    0.58
    一个月
    0.51
     günlük
    0.48
     MONTH
    0.46
    하루
    0.44
     bulan
    0.44
     вчера
    0.44
     міся
    0.43
    меся
    0.42
     hón
    0.42
    POSITIVE LOGITS
    毎年
    1.97
    每年
    1.95
     years
    1.79
     yearly
    1.72
     annually
    1.63
     year
    1.60
    years
    1.59
    Years
    1.59
     años
    1.51
     Years
    1.49
    Act Density 0.017%

    No Known Activations