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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    at
    0.88
    Untitled
    0.78
    bie
    0.74
    दीश
    0.72
    a
    0.72
     forbidden
    0.70
     wohl
    0.69
     তাঁর
    0.68
     बचाने
    0.68
    다른
    0.68
    POSITIVE LOGITS
     espos
    0.83
    tive
    0.82
     usia
    0.80
    äsident
    0.79
    рованию
    0.78
    鴦
    0.78
    檛
    0.77
    鸯
    0.75
    НЯ
    0.73
    狨
    0.73
    Act Density 0.001%

    No Known Activations