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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     direct
    0.46
     t
    0.45
     fuel
    0.44
     drug
    0.42
    fuel
    0.42
    cology
    0.42
     in
    0.41
     gear
    0.41
     brand
    0.41
     fill
    0.41
    POSITIVE LOGITS
    ہی
    0.55
    encerramento
    0.52
    নৈতিক
    0.52
    اری
    0.51
    лення
    0.50
    }\,\
    0.49
    カル
    0.48
     mergeddata
    0.48
    лега
    0.47
    પતિ
    0.47
    Act Density 0.001%

    No Known Activations