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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     વિશે
    0.50
    ^+,
    0.48
     шабло
    0.48
     μας
    0.48
     بیاکتنې
    0.47
     لیے
    0.47
     وړاندوینې
    0.46
     पढ़ाया
    0.46
     варі
    0.46
     Tijdens
    0.46
    POSITIVE LOGITS
    ਬ
    0.48
     illegal
    0.44
     biker
    0.42
     entrepreneurial
    0.42
    小
    0.42
     persons
    0.42
    said
    0.41
     mice
    0.41
     bicycl
    0.39
    抱
    0.39
    Act Density 0.005%

    No Known Activations