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

    Neuronpedia

    INDEX
    Explanations

    code blocks that look like they are autogenerated

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     getopt
    -0.50
    ScopeManager
    -0.50
     clandestine
    -0.50
    ReusableCell
    -0.48
    ม้
    -0.47
    pyrid
    -0.46
    Ancient
    -0.46
    StoreMessageInfo
    -0.45
    libft
    -0.44
     ErrIntOverflow
    -0.44
    POSITIVE LOGITS
    <bos>
    0.83
     beginnetje
    0.75
    Билгалдахарш
    0.67
    Bronnen
    0.67
     виправивши
    0.65
     ostavi
    0.65
    Tembelea
    0.64
    GEBURTSDATUM
    0.64
     HasFactory
    0.63
     linkovi
    0.62
    Act Density 1.598%

    No Known Activations