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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     scriptlevel
    0.43
    囚
    0.43
     objectifs
    0.42
     опубли
    0.42
    昨
    0.42
     sesu
    0.42
    伙
    0.42
    례
    0.42
    눙
    0.41
    림
    0.41
    POSITIVE LOGITS
    QI
    0.46
     खि
    0.44
    zenesulf
    0.41
     usually
    0.40
     through
    0.40
     stem
    0.40
    usually
    0.40
    otron
    0.40
    od
    0.40
    Ng
    0.39
    Act Density 0.008%

    No Known Activations