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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Gründe
    -0.08
     ata
    -0.07
    Gram
    -0.07
    -route
    -0.07
    hm
    -0.07
     destino
    -0.07
     пре
    -0.07
    iges
    -0.07
    hurst
    -0.07
    uges
    -0.06
    POSITIVE LOGITS
    鲷
    0.08
     Additional
    0.07
    テー�
    0.06
    计划生育
    0.06
    莿
    0.06
     Psalm
    0.06
    鲨
    0.06
    EqualityComparer
    0.06
    כנס
    0.06
    工作效率
    0.06
    Act Density 0.001%

    No Known Activations