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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     D
    0.38
     R
    0.34
     M
    0.34
     P
    0.33
     S
    0.33
     N
    0.32
     E
    0.31
     O
    0.31
     U
    0.31
    al
    0.31
    POSITIVE LOGITS
    न्होंने
    0.38
     damals
    0.33
     ubiquitin
    0.32
     этом
    0.30
    <unused2197>
    0.29
     ذلك
    0.29
     তখন
    0.29
     был
    0.29
     этой
    0.29
     его
    0.28
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.