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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     heißt
    1.08
    েনারেল
    1.05
     volgende
    1.04
     officielle
    1.02
     minions
    1.02
    encies
    1.02
     secondly
    1.01
     celebrating
    1.00
    illery
    1.00
    纜
    0.99
    POSITIVE LOGITS
     eviden
    1.34
    se
    1.32
    र
    1.31
    ן
    1.29
    ر
    1.24
    hade
    1.19
    an
    1.16
    ფ
    1.15
    িংস
    1.15
    рто
    1.15
    Act Density 0.000%

    No Known Activations