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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .
    1.02
    ed
    1.01
    ing
    1.01
    previously
    0.96
    us
    0.93
    um
    0.92
    .;
    0.90
    n
    0.88
    =
    0.88
    \_
    0.85
    POSITIVE LOGITS
     разнообраз
    1.24
    ല്ലാം
    1.23
     bets
    1.19
     pessoas
    1.16
     buget
    1.13
     Ogni
    1.12
     vš
    1.12
    aurants
    1.11
     increíble
    1.10
     люди
    1.09
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.