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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     veldig
    0.71
     talaga
    0.71
     që
    0.66
    Cuáles
    0.66
     যেগুলো
    0.65
     saudável
    0.65
    ที่เรา
    0.64
    是非常
    0.64
    这么
    0.64
     உண்
    0.63
    POSITIVE LOGITS
     decorated
    0.75
     inlaid
    0.75
     flanked
    0.74
    attrib
    0.73
     labelled
    0.69
     surmounted
    0.68
     comprising
    0.67
    unsigned
    0.66
    decorated
    0.66
     decorate
    0.64
    Act Density 0.007%

    No Known Activations