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

    Neuronpedia

    INDEX
    Explanations

    lectures and conferences

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens associated with event or meetup announcements—particularly numbers, dates, “the new” phrases, and other scheduling details.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Fruit
    -0.06
    (ex
    -0.06
    Inc
    -0.06
    İN
    -0.06
     fin
    -0.06
    _p
    -0.06
    će
    -0.06
    ocup
    -0.06
    نع
    -0.06
     traps
    -0.06
    POSITIVE LOGITS
     Analytics
    0.07
    .openapi
    0.07
     گوشی
    0.07
     올
    0.06
     základní
    0.06
    _MARKER
    0.06
    aData
    0.06
    _PHYS
    0.06
    /disable
    0.06
     привести
    0.06
    Act Density 0.032%

    No Known Activations