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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     rgba
    1.74
    ة
    1.62
    {}",
    1.61
    खु
    1.59
    ze
    1.55
    ком
    1.55
    Л
    1.54
     тим
    1.53
    Purchase
    1.50
     exh
    1.50
    POSITIVE LOGITS
     будто
    2.12
    дів
    1.94
    ような
    1.87
     să
    1.86
    𝘺
    1.82
    ח
    1.82
     uč
    1.81
     mound
    1.79
    да
    1.79
    jų
    1.73
    Act Density 0.000%

    No Known Activations