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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ringe
    -0.16
    æ£ļ
    -0.14
    تاب
    -0.13
     SpaceX
    -0.13
    _MINOR
    -0.13
     банк
    -0.13
     ÑģобоÑİ
    -0.13
    .netflix
    -0.13
     hát
    -0.13
    iÃŁ
    -0.13
    POSITIVE LOGITS
     ski
    0.43
     Ski
    0.39
     skiing
    0.35
     CCS
    0.31
    ski
    0.29
     snow
    0.29
     member
    0.27
     resorts
    0.27
    SKI
    0.26
    éĽª
    0.26
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.