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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Nik
    -0.07
    .linkedin
    -0.07
    >(),↵
    -0.07
    =np
    -0.07
    @Configuration
    -0.06
     anarchist
    -0.06
    _nm
    -0.06
    救命
    -0.06
    مستثمر
    -0.06
    别墅
    -0.06
    POSITIVE LOGITS
    رعا
    0.07
    ª
    0.07
    烘干
    0.07
     attent
    0.07
     bri
    0.07
     unre
    0.06
    (Expected
    0.06
     dying
    0.06
    局面
    0.06
    /re
    0.06
    Act Density 0.003%

    No Known Activations