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

    Neuronpedia

    INDEX
    Explanations

    accusations and legal issues

    np_max-act · gemini-2.0-flash

    The neuron is primarily detecting words and phrases describing political conflict, unrest, and forceful actions (e.g. resistance, attacks, blackmail, armed operations).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Requires
    -0.06
    dbcTemplate
    -0.06
    少し
    -0.06
     �
    -0.06
     rival
    -0.06
    More
    -0.06
    省
    -0.06
    -font
    -0.06
    HttpStatus
    -0.06
    880
    -0.06
    POSITIVE LOGITS
     {}.
    0.07
     portal
    0.06
     "\\"
    0.06
     는
    0.06
    	rep
    0.06
    edik
    0.06
     waren
    0.06
     portfolio
    0.06
    Freq
    0.06
     bursts
    0.06
    Act Density 0.059%

    No Known Activations