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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    0.41
     сред
    0.40
     европей
    0.39
    manual
    0.39
     மிகவும்
    0.39
     विश्वसनीय
    0.39
     современного
    0.39
    Рус
    0.38
    現実
    0.38
    zhong
    0.38
    POSITIVE LOGITS
     flame
    0.53
     flames
    0.53
     fury
    0.49
    火焰
    0.48
     pillars
    0.45
     fireball
    0.44
     knockout
    0.43
    换
    0.43
     breakaway
    0.42
     Flame
    0.41
    Act Density 0.002%

    No Known Activations