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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    шая
    1.04
    ー
    1.01
    ாள
    1.01
    ست
    0.99
     div
    0.97
    ют
    0.96
    ive
    0.94
    يتها
    0.93
    .[[
    0.87
    ządz
    0.87
    POSITIVE LOGITS
     kehidupan
    1.41
     quantile
    1.37
    フルーツ
    1.30
    requestId
    1.28
     undead
    1.27
    ACO
    1.25
     tộc
    1.25
    icmp
    1.24
    uction
    1.24
     regularity
    1.24
    Act Density 0.000%

    No Known Activations