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

    Neuronpedia

    INDEX
    Explanations

    time durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     semaine
    0.64
     giornata
    0.63
     week
    0.62
     teammate
    0.58
    an
    0.57
     questa
    0.57
    τ
    0.56
    ன்னை
    0.55
     compter
    0.55
    <0xA3>
    0.54
    POSITIVE LOGITS
     سنوات
    0.82
    两年
    0.78
    years
    0.66
     Years
    0.65
     Jahren
    0.63
    Observ
    0.63
     Afghans
    0.63
     Jahres
    0.62
    Years
    0.61
     años
    0.61
    Act Density 0.035%

    No Known Activations