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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    çar
    0.41
    נדה
    0.35
    ва
    0.35
    됩니다
    0.34
     Cached
    0.34
    šnji
    0.33
    مان
    0.33
    नाक
    0.33
    ших
    0.33
    sorted
    0.33
    POSITIVE LOGITS
    \%
    0.40
    0.32
     लेकर
    0.32
    𝑐
    0.32
    0.31
     $\%$
    0.31
    ॰ऍ
    0.31
    \,
    0.29
    _{(
    0.29
    𝑈
    0.29
    Act Density 0.003%

    No Known Activations