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

    Neuronpedia

    INDEX
    Explanations

    auxiliary verbs

    np_max-act · gemini-2.0-flash

    The neuron activates on long, highly specific IUPAC‐style chemical names containing multiple numeric locants and hyphens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _tmp
    -0.07
     insects
    -0.07
     legend
    -0.07
    York
    -0.06
    입니다
    -0.06
    .character
    -0.06
    PAR
    -0.06
    aniu
    -0.06
    _INCREMENT
    -0.06
     بعض
    -0.06
    POSITIVE LOGITS
    	hit
    0.07
    ær
    0.06
    (contact
    0.06
     lightning
    0.06
    })↵
    0.06
    _footer
    0.06
     penny
    0.06
     pumpkin
    0.06
    ,DB
    0.06
     '${
    0.06
    Act Density 0.006%

    No Known Activations