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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     précision
    0.81
    ádz
    0.70
    ción
    0.68
     thicknesses
    0.66
     элементов
    0.65
    要素
    0.65
     angka
    0.64
    ází
    0.64
    columnIndex
    0.63
     dàng
    0.63
    POSITIVE LOGITS
    .
    0.60
    2
    0.60
     сове
    0.60
     ilegal
    0.59
     военно
    0.56
    ش
    0.55
    向け
    0.55
    hotels
    0.54
     мало
    0.53
     starb
    0.52
    Act Density 1.128%

    No Known Activations