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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     grasp
    0.42
     dominate
    0.41
     existed
    0.41
     sian
    0.39
     isolate
    0.39
     suprem
    0.38
     extinct
    0.38
    シス
    0.38
     idiot
    0.38
     Irak
    0.38
    POSITIVE LOGITS
    受到
    0.40
     می‌شود
    0.39
     развивается
    0.38
     transduction
    0.38
    MI
    0.37
     ہو۔
    0.36
    捎
    0.36
    ந்துள்ளது
    0.36
     হয়
    0.35
    发展
    0.35
    Act Density 0.004%

    No Known Activations