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

    Neuronpedia

    INDEX
    Explanations

    the word "where"

    oai_token-act-pair · gemini-2.0-flash

    where

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -2.39
     where
    -1.90
    where
    -1.73
    Where
    -1.71
     Where
    -1.63
     WHERE
    -1.33
    WHERE
    -1.29
     donde
    -1.17
     où
    -1.08
     где
    -1.07
    POSITIVE LOGITS
    Rüyada
    0.59
    utnik
    0.58
    arcas
    0.54
    oudoune
    0.52
    ufact
    0.52
    理石
    0.52
     BOOT
    0.52
     Workbook
    0.51
    PERATURE
    0.50
    omens
    0.50
    Act Density 0.947%

    No Known Activations