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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     one
    0.99
     were
    0.99
     cinci
    0.98
     at
    0.97
     year
    0.97
     determ
    0.96
     yıl
    0.91
    月に
    0.91
     five
    0.90
     ພວກເຮົາ
    0.90
    POSITIVE LOGITS
    ként
    1.12
    ر
    1.05
    is
    1.03
    ته
    0.96
    কে
    0.96
    iszt
    0.95
    etzt
    0.95
    aría
    0.94
    kým
    0.94
    م
    0.94
    Act Density 0.000%

    No Known Activations