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

    Neuronpedia

    INDEX
    Explanations

    the word "bug" in the context of software

    oai_token-act-pair · gemini-2.0-flash

    bug

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -1.91
    ^(@)
    -1.86
     itſelf
    -1.83
     $_"
    -1.73
     photolibrary
    -1.70
     ―――――
    -1.68
     ་་
    -1.67
     myſelf
    -1.63
     $_(
    -1.61
     doubtnut
    -1.61
    POSITIVE LOGITS
     
    1.38
      
    1.34
    ↵
    1.27
     (
    1.22
     a
    1.20
    ↵↵
    1.12
     in
    1.12
     an
    1.11
    .
    1.09
    ,
    1.07
    Act Density 1.065%

    No Known Activations