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

    Neuronpedia

    INDEX
    Explanations

    Python 2 and 3 compatibility

    np_max-act · gemini-2.0-flash

    code-related syntax and definitions related to programming functions and error handling.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron strongly activates on occurrences of the Python “six” compatibility library (i.e. import/use of “six” for 2/3 compatibility).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _REGISTER
    -0.06
    悉
    -0.06
     Decoration
    -0.06
     COUNTY
    -0.06
    098
    -0.06
     düşür
    -0.06
     deter
    -0.06
     hob
    -0.06
    asta
    -0.06
    ipar
    -0.06
    POSITIVE LOGITS
     relocated
    0.07
     \'
    0.07
    "is
    0.06
    .getNode
    0.06
     rejecting
    0.06
     sido
    0.06
    博物
    0.06
     csrf
    0.06
    )}</
    0.06
     vanished
    0.06
    Act Density 0.004%

    No Known Activations