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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    0
    1.55
    1
    1.43
    <0x80>
    1.26
    </b>
    1.16
    2
    1.13
    ния
    1.07
    6
    1.04
    </h2>
    1.03
    9
    1.01
    으로
    0.99
    POSITIVE LOGITS
    。
    1.49
    $.
    1.25
    ।
    1.15
    ۔
    1.13
     it
    1.09
    in
    1.00
    g
    0.99
    loin
    0.98
    c
    0.96
    ។
    0.95
    Act Density 0.000%

    No Known Activations