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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Оси
    0.50
    нуть
    0.49
     întreb
    0.46
    HeightSizeMode
    0.45
     computations
    0.45
    $，
    0.45
     লোকেরা
    0.43
    доб
    0.42
     бушлай
    0.42
    ={}
    0.41
    POSITIVE LOGITS
    ar
    0.50
    ight
    0.50
     a
    0.50
    li
    0.50
    a
    0.46
    <unused61>
    0.44
    ↵↵↵
    0.43
    </h3>
    0.43
    ob
    0.43
    cl
    0.42
    Act Density 0.004%

    No Known Activations