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

    Neuronpedia

    INDEX
    Explanations

    authors

    np_max-act · gemini-2.0-flash

    The neuron activates on biographical summary text—sentences giving personal details (birth/death dates, occupations, notable works) in a typical encyclopedia-style entry.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    оя
    -0.06
    NSDate
    -0.06
     marriage
    -0.06
     deduct
    -0.06
     share
    -0.06
     LEFT
    -0.06
     reach
    -0.06
     barrel
    -0.06
     QUERY
    -0.06
    (hdr
    -0.06
    POSITIVE LOGITS
     Jets
    0.07
     AtomicInteger
    0.07
     thông
    0.07
    atural
    0.07
     Gri
    0.07
    öff
    0.07
    isChecked
    0.06
    Rotation
    0.06
    SOEVER
    0.06
     těla
    0.06
    Act Density 0.056%

    No Known Activations