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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     inteiro
    0.96
     hochwert
    0.94
     pacote
    0.91
     agrad
    0.88
     seja
    0.87
     armazenamento
    0.86
     acesso
    0.86
     kork
    0.86
     sred
    0.85
     segera
    0.85
    POSITIVE LOGITS
    ემა
    0.73
    均
    0.68
    也都
    0.65
    ുകളും
    0.61
    i
    0.60
    entum
    0.58
    들과
    0.55
    arele
    0.55
    fashioned
    0.54
    ğinin
    0.54
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.