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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    -\
    1.16
     tình
    1.16
    _{\
    1.05
    榄
    1.00
     r
    0.99
     うる
    0.99
    $-\
    0.99
    ^{-\
    0.98
     k
    0.97
     dieron
    0.97
    POSITIVE LOGITS
    al
    1.38
    вре
    1.38
    meth
    1.37
    alık
    1.36
    abouts
    1.30
     Conceptual
    1.29
     littered
    1.28
     রাজা
    1.27
    躇
    1.26
    мна
    1.25
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.