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

    Neuronpedia

    INDEX
    Explanations

    virtue ethics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ة
    1.92
    rations
    1.63
    ной
    1.58
    たと
    1.58
     Peny
    1.58
    érico
    1.55
    ität
    1.55
     fréquente
    1.55
    tsó
    1.53
    plots
    1.51
    POSITIVE LOGITS
     wreath
    1.80
    ഹ്ലാദ
    1.79
     fasted
    1.77
     capitalist
    1.73
    是因為
    1.72
     journalist
    1.71
     fuselage
    1.70
    ש
    1.68
     appellate
    1.66
     centerpiece
    1.64
    Act Density 0.002%

    No Known Activations