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

    Neuronpedia

    INDEX
    Explanations

    boto

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect mentions of the AWS “boto3” library (imports or boto3 client calls) in Python code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    code snippets related to using AWS services, specifically S3.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     `<
    -0.07
    _adv
    -0.06
     Puzzle
    -0.06
    _ASCII
    -0.06
     Servers
    -0.06
     square
    -0.06
    ()["
    -0.06
    jejer
    -0.06
    DEF
    -0.06
    ==
    -0.06
    POSITIVE LOGITS
     relocated
    0.09
     boto
    0.08
     florida
    0.07
    Brandon
    0.07
    (passport
    0.07
    كت
    0.07
     Fresno
    0.06
    monkey
    0.06
    .rot
    0.06
    (reply
    0.06
    Act Density 0.001%

    No Known Activations