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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Qué
    1.00
     plaus
    0.86
     दिलचस्प
    0.85
     দুর্দান্ত
    0.84
    0.84
     Jesús
    0.82
     क्विंट
    0.81
    ?!?
    0.81
     Artículo
    0.81
     Martín
    0.80
    POSITIVE LOGITS
     upto
    2.06
     atleast
    1.62
     saree
    1.50
     sarees
    1.50
     inbuilt
    1.50
     equipments
    1.39
    aadhar
    1.38
     Maharashtra
    1.30
     bollywood
    1.26
     kerala
    1.21
    Act Density 0.453%

    No Known Activations