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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    :
    0.97
    ],
    0.72
    nun
    0.68
     tí
    0.66
     называ
    0.66
    BE
    0.66
     verification
    0.66
     Verification
    0.65
    앙
    0.65
     Bible
    0.65
    POSITIVE LOGITS
    してた
    0.92
     veines
    0.89
     endroits
    0.87
     adhesives
    0.87
     hérit
    0.85
     erreurs
    0.85
     molécules
    0.84
    ㈠
    0.84
     Casas
    0.83
     adaptée
    0.83
    Act Density 0.001%

    No Known Activations