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

    Neuronpedia

    INDEX
    Explanations

    Ordinal numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     negligible
    -0.08
     underestimated
    -0.07
     общей
    -0.07
    ్రీ
    -0.07
    ే
    -0.07
     degrade
    -0.07
     degraded
    -0.07
     adjacency
    -0.07
     ут
    -0.07
    प
    -0.07
    POSITIVE LOGITS
    920
    0.09
    ocked
    0.09
     yılında
    0.08
     trazendo
    0.08
     ಕಾಂಗ್ರೆಸ್
    0.08
     trazer
    0.08
     이후
    0.08
     시대
    0.08
     trouxe
    0.08
     society
    0.08
    Act Density 0.014%

    No Known Activations