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

    Neuronpedia

    INDEX
    Explanations

    Place names

    np_max-act · gemini-2.0-flash

    This neuron fires on tokens that are part of named entities, especially proper nouns (place names and personal names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     έργ
    -0.07
     expand
    -0.07
    .Icon
    -0.07
    μένη
    -0.06
    -प
    -0.06
    ooled
    -0.06
     premiere
    -0.06
     lỗi
    -0.06
    .save
    -0.06
    .XtraBars
    -0.06
    POSITIVE LOGITS
     distracted
    0.07
    _entries
    0.06
     affecting
    0.06
     unexpected
    0.06
    <D
    0.06
     AUTHOR
    0.06
    ilece
    0.06
     اطلاع
    0.06
    IMAL
    0.06
     relics
    0.06
    Act Density 0.057%

    No Known Activations