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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    how
    1.16
    就是
    1.12
     छुट्टी
    1.11
    htp
    1.09
    У
    1.08
    ome
    1.08
    ের
    1.07
    un
    1.06
    Devil
    0.98
    up
    0.98
    POSITIVE LOGITS
     alguno
    1.43
    들은
    1.43
    们的
    1.42
    larda
    1.39
    داران
    1.38
    هاي
    1.36
    وں
    1.35
    asjoner
    1.34
    들의
    1.33
    捱
    1.32
    Act Density 2.160%

    No Known Activations