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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ergy
    -0.07
    ጅ
    -0.06
     rugby
    -0.06
    abyte
    -0.06
    林业
    -0.06
    才
    -0.06
    弄
    -0.06
     Pokemon
    -0.06
    üh
    -0.06
    发布会
    -0.06
    POSITIVE LOGITS
     moderated
    0.07
    ":
↵
    0.07
     Instructions
    0.06
     "":↵
    0.06
     largo
    0.06
     projections
    0.06
     directed
    0.06
     Zip
    0.06
    :
↵
    0.06
    (provider
    0.06
    Act Density 0.005%

    No Known Activations