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

    Neuronpedia

    INDEX
    Explanations

    function definitions and related syntax in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code-related parentheses

    np_acts-logits-general · gemini-2.0-flash

    code blocks and function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LLocation
    -0.68
     @"/
    -0.68
    CppCodeGen
    -0.61
     erythrocytes
    -0.60
     attivo
    -0.58
     Goodness
    -0.56
    ScopeManager
    -0.56
    rrggbb
    -0.56
     blessings
    -0.56
     Schles
    -0.56
    POSITIVE LOGITS
     chi̍t
    0.64
    ')))
    0.59
    ')));
    0.58
    )」
    0.55
    \""
    0.54
    ¹)
    0.53
    </s>
    0.53
    ]";
    0.52
     ++)
    0.52
    politico
    0.52
    Act Density 0.047%

    No Known Activations