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

    Neuronpedia

    INDEX
    Explanations

    technical terms and references related to software documentation and resources

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

    URLs ending in specific file extensions

    np_acts-logits-general · gemini-2.0-flash

    URL links and file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !")
    -0.80
     propOrder
    -0.76
     indisponible
    -0.74
    '],
    -0.73
    '},
    -0.72
     désolés
    -0.70
    writeFieldEnd
    -0.69
    WebElementEntity
    -0.69
     bParam
    -0.69
    ]")]
    -0.69
    POSITIVE LOGITS
    ↵↵
    0.93
    <eos>
    0.86
    #
    0.79
    ↵↵↵
    0.71
    ↵
    0.70
    \#
    0.62
    #:
    0.61
    ↵↵↵↵
    0.56
    ​
    0.56
    ?
    0.54
    Act Density 0.745%

    No Known Activations