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

    Neuronpedia

    INDEX
    Explanations

    terms related to direction, categories, types and associations

    oai_token-act-pair · gemini-2.0-flash

    directions or types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     estekak
    -1.09
    tagHelperRunner
    -1.01
    出版年
    -0.99
     AssemblyCompany
    -0.98
     consultato
    -0.96
    expandindo
    -0.96
     "..\..\..\
    -0.94
    writeFieldEnd
    -0.94
     BrowserModule
    -0.93
     Separator
    -0.93
    POSITIVE LOGITS
     the
    0.83
     in
    0.79
     and
    0.77
     to
    0.76
    ,
    0.73
     at
    0.70
     a
    0.69
     is
    0.67
     on
    0.66
     from
    0.66
    Act Density 1.318%

    No Known Activations