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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     injustices
    0.55
     injustice
    0.48
    λογή
    0.46
    льность
    0.45
     indignation
    0.45
     analogies
    0.41
    lichkeit
    0.40
     digo
    0.40
     Flinders
    0.39
     Winfrey
    0.39
    POSITIVE LOGITS
    ANE
    0.49
     કરતા
    0.44
    Á
    0.42
    +"
    0.42
     Tail
    0.42
     করিয়াছেন
    0.41
     Rotate
    0.41
     पड़ेंगे
    0.41
     శు
    0.40
    áře
    0.40
    Act Density 23.066%

    No Known Activations