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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     birçok
    0.54
    យើង
    0.53
     artı
    0.52
    ট
    0.51
    স
    0.50
    Để
    0.49
    س
    0.49
    estrian
    0.49
     inhom
    0.48
     hiçbir
    0.48
    POSITIVE LOGITS
    wahl
    0.44
     rap
    0.42
    6
    0.40
     Nodes
    0.39
     should
    0.38
    0
    0.38
    е
    0.38
    7
    0.38
     Kirk
    0.37
     Private
    0.37
    Act Density 0.001%

    No Known Activations