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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     explodes
    -0.07
     jButton
    -0.07
    佩服
    -0.07
    ậm
    -0.07
    emplate
    -0.07
    뻔
    -0.07
    兵团
    -0.07
    سرعة
    -0.07
    梅西
    -0.07
     LoginPage
    -0.07
    POSITIVE LOGITS
     Promotion
    0.07
    Lib
    0.07
    _OM
    0.07
    hyth
    0.07
    -global
    0.07
     Cov
    0.06
    범
    0.06
    관리
    0.06
    引流
    0.06
    -non
    0.06
    Act Density 0.114%

    No Known Activations