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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     individuals
    0.60
    s
    0.56
     individual
    0.52
     teaspoons
    0.51
     batteries
    0.49
    t
    0.48
     information
    0.48
     intruders
    0.47
     na
    0.47
     el
    0.47
    POSITIVE LOGITS
    ଣ
    0.50
     résulte
    0.47
    opyran
    0.47
     terminó
    0.46
    olot
    0.46
    焓
    0.46
     політи
    0.45
     discuter
    0.45
     സ്വദേശ
    0.45
    燄
    0.45
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.