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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ganhou
    0.64
    несла
    0.61
    লাভ
    0.60
    นด์
    0.59
     celu
    0.58
    িবে
    0.58
    {
    0.57
    как
    0.57
     Punkten
    0.57
    ת
    0.57
    POSITIVE LOGITS
     préférences
    0.60
     gill
    0.59
    ната
    0.57
     bepaalde
    0.57
     perils
    0.54
     checkboxes
    0.54
     gestation
    0.52
     SDGs
    0.52
     uart
    0.52
     וא
    0.51
    Act Density 0.002%

    No Known Activations