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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Такой
    1.12
    ╾
    1.02
     Chúng
    1.02
     Flexible
    1.00
     ennemis
    0.99
     Küçük
    0.99
    PlusEvents
    0.99
    ্কৃতিক
    0.99
     Pří
    0.99
    VerFile
    0.98
    POSITIVE LOGITS
     duration
    0.80
    цен
    0.73
     contrast
    0.72
    е
    0.71
     অধ্য
    0.69
    polarized
    0.69
    kin
    0.68
    ేశ
    0.67
     заве
    0.67
     ha
    0.66
    Act Density 0.000%

    No Known Activations