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

    Neuronpedia

    INDEX
    Explanations

    references to exceptions and error handling in code

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

    Code, errors, and exceptions

    np_acts-logits-general · gemini-2.0-flash

    exception or virion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.81
    Geplaatst
    -0.79
    出版年
    -0.79
    WebElementEntity
    -0.79
    twimg
    -0.79
    addCriterion
    -0.79
    pushFollow
    -0.79
    principalColumn
    -0.78
     للمعارف
    -0.77
    TagMode
    -0.77
    POSITIVE LOGITS
     e
    0.64
     ex
    0.61
    e
    0.59
     |
    0.56
    Exception
    0.54
    ignored
    0.54
     exception
    0.54
    xae
    0.54
     laikā
    0.52
    ex
    0.51
    Act Density 0.019%

    No Known Activations