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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    _SMALL
    -0.07
    知识分子
    -0.07
    \Database
    -0.07
    Stand
    -0.07
    _space
    -0.07
     beforehand
    -0.07
     monstr
    -0.07
    念头
    -0.07
    _syn
    -0.07
    钭
    -0.06
    POSITIVE LOGITS
    狐月山
    0.07
     graz
    0.06
    лен
    0.06
     vomiting
    0.06
    鲵
    0.06
     teachers
    0.06
    帰
    0.06
    ⲣ
    0.06
    	ns
    0.06
     wireless
    0.06
    Act Density 0.016%

    No Known Activations