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

    Neuronpedia

    INDEX
    Explanations

    an

    np_max-act · gemini-2.0-flash

    This neuron fires on named entities—especially film titles, actor/character names, and other proper nouns.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _pw
    -0.06
    吃
    -0.06
    �
    -0.06
    _VISIBLE
    -0.06
    Store
    -0.06
     damages
    -0.06
    .Priority
    -0.06
     nuclear
    -0.06
     등록
    -0.06
     medio
    -0.06
    POSITIVE LOGITS
     situation
    0.06
     legally
    0.06
    books
    0.06
     parad
    0.06
    纸
    0.06
    ινή
    0.06
    ským
    0.06
    >alert
    0.06
     BEEN
    0.06
    ανδ
    0.06
    Act Density 0.015%

    No Known Activations