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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ╧
    1.22
     SIINFEKL
    1.20
    cles
    1.19
     !_
    1.17
     ply
    1.15
    ˶
    1.15
     són
    1.10
    なんと
    1.09
     antisymmetric
    1.07
    тить
    1.07
    POSITIVE LOGITS
    al
    1.32
    可能性
    1.09
    ы
    1.06
    ing
    1.05
    ेड
    1.04
     Climate
    1.02
    ुस्तान
    0.98
    alura
    0.98
    ੜ
    0.97
     Secular
    0.97
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.