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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Sam
    0.52
     Copyright
    0.52
     Nether
    0.50
     How
    0.48
     Copy
    0.48
    Q
    0.47
     Constant
    0.47
    Sh
    0.47
     Flow
    0.47
     Q
    0.46
    POSITIVE LOGITS
     opción
    0.80
     opcao
    0.70
     opção
    0.67
     opciones
    0.65
     parámetros
    0.65
     solución
    0.64
    OPTION
    0.62
    option
    0.61
     estimular
    0.60
     presentada
    0.58
    Act Density 0.000%

    No Known Activations