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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    0.70
     Beur
    0.68
     Francisco
    0.67
     Regions
    0.67
     fromi
    0.66
     prosent
    0.66
     Juillet
    0.65
     CENTRE
    0.65
     carénés
    0.65
     MICHAEL
    0.65
    POSITIVE LOGITS
     다
    0.61
     poderão
    0.58
    С
    0.58
    ılmaz
    0.55
     সিম
    0.54
    плю
    0.54
     нам
    0.53
    лог
    0.53
     смогут
    0.52
    У
    0.52
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.