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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     nano
    -0.08
    𝒸
    -0.08
    的心情
    -0.08
    observe
    -0.07
     unbe
    -0.07
     Saunders
    -0.07
    Converter
    -0.07
    反而
    -0.07
    even
    -0.07
    胗
    -0.07
    POSITIVE LOGITS
    _material
    0.08
    嚴
    0.07
     región
    0.07
     meny
    0.07
    レイ
    0.07
    //--------------------------------
    0.07
    地域
    0.07
    旗帜
    0.07
    _ARB
    0.06
    אפי
    0.06
    Act Density 0.011%

    No Known Activations