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

    Neuronpedia

    INDEX
    Explanations

    consecutive sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     помимо
    0.75
     универса
    0.74
     asymmetries
    0.69
     ترم
    0.67
     univerz
    0.67
     divert
    0.67
     asymmetry
    0.66
     universal
    0.63
     Varsity
    0.62
     vencedor
    0.62
    POSITIVE LOGITS
     consecutive
    3.35
     Consecutive
    2.97
     consecutively
    2.97
     consecut
    2.69
     sequential
    2.47
     successive
    2.46
     연속
    2.41
    Consec
    2.34
     consecutivos
    2.27
    连续
    2.22
    Act Density 0.310%

    No Known Activations