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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     is
    0.87
     eternal
    0.79
    0.78
     amazing
    0.77
     Earth
    0.76
     perfect
    0.75
     your
    0.73
     laws
    0.72
     terrifying
    0.71
     science
    0.71
    POSITIVE LOGITS
     തീരുമാന
    0.95
     Özellikle
    0.95
     अपेक्षाकृत
    0.95
     Priorities
    0.92
     szczególnie
    0.91
    nocześnie
    0.90
     unanticipated
    0.90
     부담
    0.89
    特定の
    0.88
     بعض
    0.87
    Act Density 0.000%

    No Known Activations