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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ς
    1.88
     Πα
    1.60
    י
    1.56
    潘
    1.54
    𝘴
    1.52
    нення
    1.52
    스러운
    1.50
    т
    1.48
    ে
    1.46
    ></
    1.41
    POSITIVE LOGITS
    ay
    1.87
    ong
    1.72
    ون
    1.68
     ساختمان
    1.62
     Skyscrapers
    1.56
    то
    1.48
    মান
    1.48
     izgrad
    1.46
    ार
    1.45
    ال
    1.45
    Act Density 0.268%

    No Known Activations