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

    Neuronpedia

    INDEX
    Explanations

    uicolor

    np_max-act · gemini-2.0-flash

    The neuron fires on the “Q:” and “A:” markers that delimit questions and answers in the post.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Wikispecies
    -0.07
    _MAGIC
    -0.07
    lixir
    -0.07
     lent
    -0.07
     Mant
    -0.06
    bo
    -0.06
     Tab
    -0.06
    prot
    -0.06
    rente
    -0.06
     lem
    -0.06
    POSITIVE LOGITS
    自动
    0.07
     Years
    0.07
     CLUB
    0.06
     üy
    0.06
     RowBox
    0.06
     tickets
    0.06
     Ricky
    0.06
    _STYLE
    0.06
     CSV
    0.06
    Modified
    0.06
    Act Density 0.002%

    No Known Activations