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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    宫廷
    -0.08
     SimpleName
    -0.08
    ElementsBy
    -0.07
    _macro
    -0.07
    ilyn
    -0.07
    민
    -0.07
    泮
    -0.07
    ?key
    -0.07
    Begin
    -0.07
    _EXTERN
    -0.07
    POSITIVE LOGITS
    باء
    0.08
     Patterns
    0.08
    Dao
    0.07
    pas
    0.07
    ña
    0.07
    🚼
    0.07
    	thread
    0.07
     Ma
    0.07
    %).
    0.07
    wy
    0.07
    Act Density 0.002%

    No Known Activations