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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    </h2>
    1.07
    k
    1.00
     by
    0.97
    ן
    0.97
    kita
    0.96
    Message
    0.94
    Data
    0.93
     it
    0.93
    Statement
    0.93
    keb
    0.91
    POSITIVE LOGITS
    ра
    1.58
    al
    1.48
    к
    1.30
    ле
    1.19
    м
    1.16
    ли
    1.12
    то
    1.11
    т
    1.10
    не
    1.04
    이다
    1.04
    Act Density 0.000%

    No Known Activations