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

    Neuronpedia

    INDEX
    Explanations

    the word "to"

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -1.80
    Personensuche
    -1.08
     nahilalakip
    -1.07
    UnusedPrivate
    -1.05
    AsUp
    -1.05
     '\\;'
    -1.05
    LookAnd
    -1.02
     AssemblyCulture
    -1.02
    цездатний
    -1.02
    uxxxx
    -1.00
    POSITIVE LOGITS
     more
    0.69
     it
    0.69
     some
    0.69
     many
    0.67
     various
    0.67
     a
    0.66
     as
    0.66
     most
    0.65
     if
    0.65
     the
    0.65
    Act Density 1.287%

    No Known Activations