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

    Neuronpedia

    INDEX
    Explanations

    markdown

    np_max-act · gemini-2.0-flash

    This neuron detects the “markdown” cell-type markers (i.e. the occurrences of the word “markdown” in the notebook JSON).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    VAS
    -0.08
    jections
    -0.07
    βι
    -0.07
    ΕΛ
    -0.06
    `.
    -0.06
     Abr
    -0.06
     unc
    -0.06
     většinou
    -0.06
     Chap
    -0.06
     Liber
    -0.06
    POSITIVE LOGITS
    ोज
    0.07
     жел
    0.07
    (Sql
    0.07
     Toolbox
    0.07
    <pre
    0.06
    .DateTime
    0.06
    订单
    0.06
    ForRow
    0.06
    	widget
    0.06
    Status
    0.06
    Act Density 0.001%

    No Known Activations