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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    يلا
    1.25
    大
    1.17
     présentent
    1.16
    ीट
    1.02
    两
    1.01
    大脑
    0.99
    يا
    0.98
     бір
    0.97
    ほうが
    0.97
    ，
    0.96
    POSITIVE LOGITS
    _
    1.43
    \
    1.34
    (
    1.23
    si
    1.20
    ta
    1.17
    ’
    1.17
    д
    1.16
    ка
    1.16
    in
    1.15
    sl
    1.13
    Act Density 0.000%

    No Known Activations