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

    Neuronpedia

    INDEX
    Explanations

    Software development

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens characteristic of code or configuration text—uppercase identifiers, tool and file names, option flags, numeric versions, and similar technical jargon.

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

    technical terms and configurations related to programming and software development.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Ant
    -0.06
     욕
    -0.06
     εκ
    -0.06
     等
    -0.06
     Simon
    -0.06
    国内
    -0.06
    Simon
    -0.06
     Across
    -0.06
    Apps
    -0.06
    等
    -0.06
    POSITIVE LOGITS
    Namespace
    0.07
    σφα
    0.07
    ูร
    0.06
    (itr
    0.06
    ایسه
    0.06
    creates
    0.06
    plain
    0.06
    ,)
    0.06
    _EXPI
    0.06
     shootout
    0.06
    Act Density 0.034%

    No Known Activations