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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ната
    0.80
    ције
    0.78
    ନା
    0.78
    ൽപ്പന
    0.77
    impse
    0.75
    питан
    0.75
    гато
    0.74
    рос
    0.73
    Tarjeta
    0.73
     utilisateurs
    0.73
    POSITIVE LOGITS
    种
    0.98
    痴
    0.77
    int
    0.75
    ड़े
    0.74
    hop
    0.74
    yloxy
    0.72
    फुल
    0.72
    ase
    0.70
     \%
    0.70
    ha
    0.70
    Act Density 0.001%

    No Known Activations