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

    Neuronpedia

    INDEX
    Explanations

    f

    np_max-act · gemini-2.0-flash

    This neuron fires on document‐structure markers—e.g. section headings and labels—such as chapter numbers (and their following commas), “API”/“Response” tags, and other heading‐style punctuation.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    +","+
    -0.07
     SOM
    -0.06
     METHOD
    -0.06
    handleRequest
    -0.06
     gio
    -0.06
     resumes
    -0.06
     cắt
    -0.06
     frequ
    -0.06
     προσ
    -0.06
     thresh
    -0.06
    POSITIVE LOGITS
    ╝
    0.07
      	↵
    0.06
    MYSQL
    0.06
     genuine
    0.06
    ingly
    0.06
     ;
    0.06
    (rgb
    0.06
    ns
    0.06
    važ
    0.06
     alongside
    0.06
    Act Density 0.000%

    No Known Activations