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

    Neuronpedia

    INDEX
    Explanations

    a/an

    np_max-act · gemini-2.0-flash

    The neuron fires on the typical news‐lead opening “In a …” phrase (e.g. “In a bid…,” “In a recent ruling…,” “In a severe indictment…”) that introduces a story.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ideas
    -0.07
    beits
    -0.07
    기가
    -0.07
    ãy
    -0.07
    (sh
    -0.06
    editor
    -0.06
     rulers
    -0.06
    iper
    -0.06
     discussions
    -0.06
     concepts
    -0.06
    POSITIVE LOGITS
    ----↵
    0.07
    due
    0.07
     bedeut
    0.07
    =='
    0.06
    .'
    0.06
     condo
    0.06
     Speaking
    0.06
    ､↵
    0.06
    omic
    0.06
     *,↵
    0.06
    Act Density 0.015%

    No Known Activations