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

    Neuronpedia

    INDEX
    Explanations

    Historical context

    np_max-act · gemini-2.0-flash

    biographical details about historical figures, particularly in the fields of art, science, and entertainment.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron responds to discourse markers and emphasis words (especially ordinals and temporal/transition adverbs like “first,” “later,” “particularly,” “among,” etc.) that introduce or highlight key points.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    FU
    -0.07
     Clintons
    -0.06
    enen
    -0.06
    发展
    -0.06
    (local
    -0.06
    Thomas
    -0.06
    osate
    -0.06
     memor
    -0.06
     mRNA
    -0.06
    rost
    -0.06
    POSITIVE LOGITS
     newList
    0.06
    roduction
    0.06
    guide
    0.06
     Albums
    0.06
    %).↵↵
    0.06
    :NSUTF
    0.06
    uppe
    0.05
    оян
    0.05
    asily
    0.05
     Declare
    0.05
    Act Density 0.058%

    No Known Activations