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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ঘিরে
    0.44
    ătoare
    0.44
     hof
    0.43
     предпочита
    0.43
    充满
    0.42
     wydar
    0.41
    为何
    0.40
    lobal
    0.40
    ॉ
    0.40
    Пе
    0.39
    POSITIVE LOGITS
     prejudices
    0.47
     mencion
    0.45
     inquest
    0.45
     miserable
    0.44
     apoy
    0.44
     bruit
    0.44
     inning
    0.44
     scru
    0.43
     injurious
    0.43
     injury
    0.42
    Act Density 0.006%

    No Known Activations