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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    </b>
    1.50
    </h2>
    1.41
    <0x0D>
    1.30
    </u>
    1.23
    ↵
    1.14
    </h1>
    1.14
    ся
    1.10
    </code>
    1.03
    <unused60>
    0.99
    ají
    0.96
    POSITIVE LOGITS
    1.50
    n
    1.34
    at
    1.27
    re
    1.23
    am
    1.14
     bouts
    1.12
    f
    1.09
     wilds
    1.05
    s
    1.04
    d
    1.02
    Act Density 0.000%

    No Known Activations