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

    Neuronpedia

    INDEX
    Explanations

    sports leagues and debuts

    np_max-act · gemini-2.0-flash

    This neuron fires on capitalized name tokens, particularly parts of people’s names (proper nouns).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Nicole
    -0.07
     ae
    -0.06
    PLIC
    -0.06
    /navbar
    -0.06
    FolderPath
    -0.06
     CAS
    -0.06
     Flow
    -0.06
    (uint
    -0.06
     cous
    -0.06
    _reload
    -0.06
    POSITIVE LOGITS
    Grand
    0.08
     učitel
    0.07
    />.
    0.07
    />↵↵
    0.07
    ило
    0.07
    =\"
    0.07
     em
    0.06
     gaping
    0.06
    _hdr
    0.06
     geçmiş
    0.06
    Act Density 0.025%

    No Known Activations