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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    אן
    1.63
    ib
    1.60
    oc
    1.59
    zov
    1.59
    ic
    1.57
    ar
    1.55
    ě
    1.53
    anine
    1.50
    icel
    1.50
    ো
    1.50
    POSITIVE LOGITS
     antérieure
    1.84
     intégr
    1.73
     différente
    1.69
    ibilités
    1.67
     pleinement
    1.66
    骜
    1.66
     dépens
    1.49
     énorm
    1.48
    이드
    1.48
    дят
    1.47
    Act Density 0.881%

    No Known Activations