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

    Neuronpedia

    INDEX
    Explanations

    the closing braces in code blocks

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

    Code snippets or program-related text

    np_acts-logits-general · gemini-2.0-flash

    sees human, the primary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TextAppearance
    -0.76
    GOTREF
    -0.51
    wpi
    -0.50
    Демографія
    -0.49
    thyst
    -0.48
    jestel
    -0.47
    ValueStyle
    -0.47
     guardia
    -0.47
     Sucher
    -0.46
     informée
    -0.46
    POSITIVE LOGITS
    GEBURTSDATUM
    0.60
    expandindo
    0.59
    :✨
    0.57
    __':
    0.55
     OMITBAD
    0.54
    invokeLater
    0.53
    yargs
    0.52
    endsection
    0.51
    interopRequire
    0.50
    migrationBuilder
    0.50
    Act Density 0.045%

    No Known Activations