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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    kannya
    1.28
    deque
    1.22
    ogany
    1.17
    tains
    1.15
     crushed
    1.15
    تها
    1.14
    scripts
    1.13
    шую
    1.11
    distances
    1.10
     baseUrl
    1.09
    POSITIVE LOGITS
    ر
    1.37
    ्ञ
    1.33
    る
    1.30
    ी
    1.20
     ग्राह
    1.19
    з
    1.13
    ы
    1.12
    讒
    1.09
     capp
    1.07
    PIA
    1.03
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.