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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    发财
    -0.07
     Cộng
    -0.07
    Orange
    -0.07
    SetBranch
    -0.07
    个多月
    -0.07
    分化
    -0.06
    寺
    -0.06
    +Sans
    -0.06
    _zoom
    -0.06
    公安
    -0.06
    POSITIVE LOGITS
     bitwise
    0.08
    🏿
    0.07
    ✇
    0.07
     turmoil
    0.07
     rusty
    0.07
    posal
    0.07
         ↵
    0.07
     پ
    0.06
    ercial
    0.06
     pedestal
    0.06
    Act Density 0.034%

    No Known Activations