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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Rug
    0.55
    Rug
    0.55
     Marion
    0.55
    Shir
    0.54
    Marion
    0.54
     merge
    0.52
    Transport
    0.52
    更多
    0.51
    Shiv
    0.51
    转载
    0.50
    POSITIVE LOGITS
     verità
    0.67
     왜
    0.66
     refresher
    0.63
     extrêmement
    0.62
     エン
    0.61
     quyết
    0.60
     mérite
    0.60
     advantages
    0.60
     लाभदायक
    0.59
     benefícios
    0.58
    Act Density 0.000%

    No Known Activations