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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ab
    0.42
     ar
    0.42
    说的
    0.41
     Pole
    0.39
    рах
    0.39
    adjacency
    0.38
    ❒
    0.38
    Wah
    0.38
     aug
    0.38
    Nep
    0.38
    POSITIVE LOGITS
     silenz
    0.41
    酰
    0.39
     ബി
    0.39
     silenc
    0.38
    ilea
    0.38
     bi
    0.38
    CurrentByte
    0.36
    ലെസ്
    0.36
    甲基
    0.35
    rops
    0.35
    Act Density 0.000%

    No Known Activations