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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    _keyboard
    -0.07
    obby
    -0.07
     corporation
    -0.07
    喏
    -0.07
     dụ
    -0.07
    .rstrip
    -0.07
    ZR
    -0.06
    保健品
    -0.06
    話
    -0.06
    咦
    -0.06
    POSITIVE LOGITS
    (t
    0.07
     late
    0.07
     Mult
    0.07
    发光
    0.07
    进出
    0.06
    科创
    0.06
    .yang
    0.06
    踉
    0.06
    Lines
    0.06
    ("-",
    0.06
    Act Density 0.867%

    No Known Activations