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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Bad
    0.66
     Articles
    0.64
     citizenship
    0.62
     Laws
    0.60
     articles
    0.59
     bad
    0.59
     certified
    0.58
     Δεν
    0.58
     requirements
    0.57
     Article
    0.57
    POSITIVE LOGITS
     nayo
    0.67
    winds
    0.66
    瑭
    0.64
    among
    0.63
    injlim
    0.60
    나
    0.60
     utilisant
    0.59
     nhờ
    0.59
     leverages
    0.59
    समोर
    0.58
    Act Density 0.012%

    No Known Activations