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

    Neuronpedia

    INDEX
    Explanations

    helicopter

    np_max-act · gemini-2.0-flash

    This neuron detects domain-specific or proper-noun keywords (e.g., names of technologies, organizations, or markets).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    換
    -0.06
     vyrob
    -0.06
    _VALID
    -0.06
    _WR
    -0.06
     форму
    -0.06
     آمده
    -0.06
    惠
    -0.06
    _refresh
    -0.06
    شتر
    -0.06
    筑
    -0.06
    POSITIVE LOGITS
    sgiving
    0.07
    (state
    0.06
    isSelected
    0.06
     appellant
    0.06
     řízení
    0.06
     Thanksgiving
    0.06
     franchises
    0.06
     Kyle
    0.06
     Cosmos
    0.06
     antioxidants
    0.06
    Act Density 0.210%

    No Known Activations