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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     confronti
    1.28
     имена
    1.24
    ﻪ
    1.24
    اليه
    1.21
    ostiene
    1.18
    boli
    1.18
    ﮕ
    1.17
    rollback
    1.16
     प्रय
    1.15
     Kristi
    1.14
    POSITIVE LOGITS
    ン
    1.15
    キュリティ
    1.06
    於
    1.04
    腔
    0.99
     패
    0.94
    패
    0.92
    sion
    0.91
    為
    0.90
     把
    0.89
     hyst
    0.89
    Act Density 0.000%

    No Known Activations