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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron fires on section-title or heading tokens that introduce new parts of an article (e.g. “Definition,” “Background,” “History,” “Statistical model,” “United,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Dataset
    -0.07
    YW
    -0.06
    	ev
    -0.06
    /user
    -0.06
     khăn
    -0.06
     lain
    -0.06
     超
    -0.06
     ICON
    -0.06
    	dc
    -0.06
    似的
    -0.06
    POSITIVE LOGITS
    .fix
    0.06
     गर
    0.06
     дог
    0.06
     NSAttributedString
    0.06
    ремя
    0.06
    .ptr
    0.06
    olo
    0.06
     significant
    0.06
     #{@
    0.06
     mest
    0.06
    Act Density 0.032%

    No Known Activations