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

    Neuronpedia

    INDEX
    Explanations

    Press

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the word “Press” in the context of the news‐wire credit (e.g. “Associated Press”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    建
    -0.07
    _X
    -0.06
     wordt
    -0.06
    _fragment
    -0.06
     Unt
    -0.06
    _save
    -0.06
    ัย
    -0.06
    ante
    -0.06
    uito
    -0.06
     Ir
    -0.06
    POSITIVE LOGITS
     AP
    0.08
    /AP
    0.07
    ')");↵
    0.07
     battleground
    0.07
     bulun
    0.07
    ้องการ
    0.07
     ｰ
    0.07
     CRUD
    0.07
    (express
    0.07
    bid
    0.07
    Act Density 0.003%

    No Known Activations