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

    Neuronpedia

    INDEX
    Explanations

    filtering with where

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eröff
    0.70
    Kemudian
    0.63
     tacked
    0.63
     Sebelumnya
    0.62
     Walt
    0.61
     sẵn
    0.61
    uncak
    0.61
     majd
    0.61
    üll
    0.60
    न्द्रीय
    0.60
    POSITIVE LOGITS
    filter
    1.39
     filtering
    1.35
     where
    1.35
     filtered
    1.35
     Filter
    1.32
     filter
    1.32
     filtrar
    1.31
     WHERE
    1.27
     Filtering
    1.27
    Filtering
    1.27
    Act Density 0.363%

    No Known Activations