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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     האינטרנט
    -0.07
    有任何
    -0.07
     답
    -0.07
    nergie
    -0.07
    ользов
    -0.07
    <Resource
    -0.07
     tác
    -0.07
    REMOTE
    -0.07
     tồn
    -0.07
    번
    -0.06
    POSITIVE LOGITS
    第一章
    0.08
     ikea
    0.07
     Spears
    0.07
     jumping
    0.07
     ↵↵↵
    0.07
     bill
    0.07
     leaking
    0.07
    【
    0.07
    ):
↵
↵
    0.07
    大涨
    0.07
    Act Density 0.008%

    No Known Activations