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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Об
    0.55
    ,
    0.54
    '
    0.54
    的气
    0.53
    нина
    0.53
     unten
    0.52
    ian
    0.52
    ’
    0.51
    \
    0.50
    కు
    0.50
    POSITIVE LOGITS
     internal
    1.23
    Internal
    1.14
     Internal
    1.14
    internal
    1.05
     interne
    1.05
    INTERNAL
    0.92
     internes
    0.91
     internally
    0.91
     wewnętr
    0.90
     내부
    0.89
    Act Density 0.022%

    No Known Activations