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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     takes
    0.99
     has
    0.95
     this
    0.94
     it
    0.93
     ordinances
    0.90
     took
    0.89
     summarizes
    0.89
    सूर्य
    0.89
     certifies
    0.88
     that
    0.87
    POSITIVE LOGITS
    ी
    0.80
    логия
    0.79
     координа
    0.75
    ен
    0.74
    𝕠
    0.73
    хову
    0.73
    او
    0.69
     фина
    0.69
     وع
    0.68
     desf
    0.68
    Act Density 0.000%

    No Known Activations