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

    Neuronpedia

    INDEX
    Explanations

    log messages and error handling statements in the text

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

    Log messages: warn, error, info, debug

    np_acts-logits-general · gemini-2.0-flash

    logging levels and errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "/",
    -0.68
    <?
    -0.63
    aarrggbb
    -0.62
     Roskov
    -0.60
    TestingModule
    -0.59
     AssemblyCulture
    -0.58
    RegistryLite
    -0.57
    '/',
    -0.55
    Compat
    -0.54
     "="
    -0.53
    POSITIVE LOGITS
     sprintf
    0.68
    sprintf
    0.65
    SequentialGroup
    0.56
    Sprintf
    0.56
    Crossref
    0.54
     SAI
    0.53
     unangemessene
    0.53
    nadequate
    0.51
     tantum
    0.51
    ﷺ
    0.51
    Act Density 0.082%

    No Known Activations