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

    Neuronpedia

    INDEX
    Explanations

    China/Chinese culture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    errHandler
    -0.51
    ftagPool
    -0.50
    ngdoc
    -0.50
     Monfieur
    -0.50
    subsubsection
    -0.49
    cycline
    -0.49
    objetivo
    -0.47
     Failing
    -0.47
    ArgumentParser
    -0.47
     offending
    -0.46
    POSITIVE LOGITS
    脚注の使い方
    0.61
    \{\\
    0.60
     مشين
    0.58
    󠁢
    0.54
    abestanden
    0.54
     <",
    0.53
     [*]
    0.52
    الإنجليزية
    0.51
     numberOfRows
    0.50
    NUMX
    0.50
    Act Density 0.022%

    No Known Activations