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

    Neuronpedia

    INDEX
    Explanations

    interest

    np_max-act · gemini-2.0-flash

    This neuron detects structural markup tokens and metadata (e.g. conversation role tags and special delimiters) rather than actual content.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    pees
    -0.06
     Parses
    -0.06
    mdat
    -0.06
    ९
    -0.06
    鲁
    -0.06
     Scheduler
    -0.05
    literal
    -0.05
     weeks
    -0.05
    	code
    -0.05
    _BIT
    -0.05
    POSITIVE LOGITS
    /ubuntu
    0.07
     algorithm
    0.07
     occured
    0.07
    Scheme
    0.07
     AFF
    0.07
     کارخانه
    0.07
     concl
    0.07
     uplift
    0.06
    artisan
    0.06
    /admin
    0.06
    Act Density 0.006%

    No Known Activations