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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Commence
    1.26
     Бере
    1.25
     વધ
    1.25
    ually
    1.23
    ceeded
    1.23
    dollars
    1.22
    ources
    1.22
    ais
    1.22
    spedes
    1.18
     ورځې
    1.17
    POSITIVE LOGITS
     πως
    1.20
    켄
    1.10
    ின்
    1.03
    剂
    1.01
     tropical
    1.00
    보고
    1.00
    kker
    0.98
    etar
    0.96
    ുടെ
    0.95
    스의
    0.94
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.