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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ഏ
    0.89
    Những
    0.81
    ية
    0.80
     aiuto
    0.80
     risol
    0.79
    mujer
    0.77
    También
    0.75
     hãy
    0.73
     élevées
    0.73
     점
    0.73
    POSITIVE LOGITS
    θηκε
    0.74
    зен
    0.71
     Sociology
    0.71
     Decree
    0.71
    achment
    0.71
    рифт
    0.70
     Jumat
    0.69
     Dump
    0.68
    -​
    0.68
     Dining
    0.67
    Act Density 0.020%

    No Known Activations