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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    	game
    -0.07
     Andersen
    -0.07
    /student
    -0.07
     kişi
    -0.07
    入学
    -0.07
    _ordered
    -0.06
     Enterprises
    -0.06
     Lö
    -0.06
    있는
    -0.06
    _least
    -0.06
    POSITIVE LOGITS
    ↵↵↵
    0.07
    将迎来
    0.07
    ই
    0.07
    ల
    0.06
    توجيه
    0.06
    <UnityEngine
    0.06
    (-
    0.06
    十
    0.06
    Curr
    0.06
     ps
    0.06
    Act Density 0.159%

    No Known Activations