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

    Neuronpedia

    INDEX
    Explanations

    numbers 9, 11, 21

    np_max-act · gemini-2.0-flash

    metrics or statistics related to code coverage in software development.

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

    This neuron detects numeric tokens used as line numbers or list indices.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    az
    -0.06
     lạc
    -0.06
     vod
    -0.06
     pus
    -0.06
    atar
    -0.06
    :&
    -0.06
    ATAR
    -0.06
    ”
    -0.06
    _Font
    -0.06
     RAD
    -0.06
    POSITIVE LOGITS
     -$
    0.07
    (actions
    0.06
     deported
    0.06
     searchBar
    0.06
     nowrap
    0.06
     ✔
    0.06
    -widget
    0.06
     soared
    0.06
    _finished
    0.06
    	tx
    0.06
    Act Density 0.003%

    No Known Activations