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

    Neuronpedia

    INDEX
    Explanations

    );

    np_max-act · gemini-2.0-flash

    This neuron responds to legal citation strings, especially reporter references with volume numbers, abbreviations (e.g. Fed. R. App. P.), parenthetical subsections, and circuit or page identifiers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    159
    -0.07
     outnumber
    -0.07
    thumb
    -0.07
    cloth
    -0.06
    	friend
    -0.06
    마트
    -0.06
     LRV
    -0.06
     Communities
    -0.06
     fromDate
    -0.06
    	stat
    -0.06
    POSITIVE LOGITS
    .modules
    0.06
    QU
    0.06
    상
    0.06
    _params
    0.06
     sinking
    0.06
    -less
    0.06
    rench
    0.06
     Pres
    0.05
    Scaling
    0.05
    <Message
    0.05
    Act Density 0.006%

    No Known Activations