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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     مختلف
    0.54
     nejen
    0.50
    我要
    0.49
     lengthy
    0.48
     거
    0.47
     all
    0.46
    да
    0.46
    га
    0.46
    بغ
    0.46
     समस्त
    0.46
    POSITIVE LOGITS
     apenas
    1.13
     $(<
    1.02
    penas
    0.90
     slechts
    0.90
     (\<
    0.88
    🤏
    0.88
     (<
    0.87
     лишь
    0.85
     limitada
    0.84
     only
    0.83
    Act Density 0.037%

    No Known Activations