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

    Neuronpedia

    INDEX
    Explanations

    open

    np_max-act · gemini-2.0-flash

    The neuron fires on the subword “open” (as in the middle of “thrombocytopenia”), flagging that specific sequence within longer medical terms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     �
    -0.07
     BTC
    -0.06
    rdf
    -0.06
    参数
    -0.06
    Headers
    -0.06
    ště
    -0.06
    _L
    -0.06
    altet
    -0.06
    (Util
    -0.06
    proxy
    -0.06
    POSITIVE LOGITS
    immers
    0.08
    िवस
    0.07
     Fam
    0.07
    ultiply
    0.06
    AN
    0.06
    寺
    0.06
    icate
    0.06
     کم
    0.06
     ICMP
    0.06
    egrate
    0.06
    Act Density 0.001%

    No Known Activations