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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     района
    0.86
    geqslant
    0.77
    🙅
    0.77
    до
    0.76
     coals
    0.74
    م
    0.73
     missiles
    0.72
    ❤️❤️
    0.72
    🙇
    0.72
     যাবত
    0.71
    POSITIVE LOGITS
     bizarre
    1.09
    Strange
    1.09
     strange
    1.08
    奇怪
    1.08
    独特的
    1.06
     lạ
    1.02
     अनो
    1.01
     sorprendente
    1.01
     extraño
    1.00
     অদ্ভুত
    1.00
    Act Density 0.240%

    No Known Activations