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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     अरुण
    0.50
    pentine
    0.49
     Meskipun
    0.49
     actitud
    0.48
    เปล
    0.48
     abdomen
    0.48
    posure
    0.47
     abhor
    0.47
    バラ
    0.47
    ✷
    0.46
    POSITIVE LOGITS
    bibitem
    0.40
    help
    0.39
     prí
    0.39
     honorary
    0.39
    caption
    0.38
     என்ப
    0.38
     piloto
    0.37
     claimed
    0.37
     title
    0.37
     sponsored
    0.37
    Act Density 0.000%

    No Known Activations