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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Cd
    -0.08
    微博
    -0.08
    lke
    -0.08
    سلاح
    -0.07
    NoArgsConstructor
    -0.07
    弧
    -0.07
     very
    -0.07
     vg
    -0.07
    皇家
    -0.06
    的灵魂
    -0.06
    POSITIVE LOGITS
     Eva
    0.09
    -frame
    0.08
    窗
    0.07
    frey
    0.07
    мет
    0.07
    (schema
    0.07
    赏析
    0.07
     gra
    0.07
    _emails
    0.07
    能否
    0.06
    Act Density 0.001%

    No Known Activations