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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    강
    -0.08
    .SubItems
    -0.08
     Never
    -0.07
    殇
    -0.07
    狐月山
    -0.07
     relatives
    -0.07
    คนไทย
    -0.07
    initialized
    -0.07
    瞽
    -0.07
     Zhang
    -0.07
    POSITIVE LOGITS
    갗
    0.07
    ):
↵
    0.07
    our
    0.07
    Region
    0.07
    odom
    0.07
    ):↵
    0.07
     sorts
    0.06
    페
    0.06
    からの
    0.06
     tiles
    0.06
    Act Density 0.004%

    No Known Activations