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

    Neuronpedia

    INDEX
    Explanations

    medical texts

    np_max-act · gemini-2.0-flash

    The neuron detects recommendation language—phrases that propose including or incorporating something (e.g. “should be part of,” “include,” “incorporated into”) into a protocol, test battery, or differential diagnosis.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     своими
    -0.07
     catalogs
    -0.07
    .usage
    -0.06
     :]
    -0.06
     tableView
    -0.06
     accrued
    -0.06
    .ant
    -0.06
     except
    -0.06
     Notices
    -0.06
     olan
    -0.06
    POSITIVE LOGITS
    шла
    0.07
     GetLastError
    0.07
    .П
    0.07
     opendir
    0.07
    τικού
    0.07
    	NullCheck
    0.07
    edImage
    0.06
    (prompt
    0.06
    /blue
    0.06
     geçti
    0.06
    Act Density 0.035%

    No Known Activations