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

    Neuronpedia

    INDEX
    Explanations

    Cuisine

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of a cuisine or food style (e.g., “Korean food,” “cuisine,” “gastronomic”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ampp
    -0.08
    high
    -0.08
     Robots
    -0.07
     Harold
    -0.07
    _top
    -0.07
     High
    -0.07
    _Local
    -0.07
    actionDate
    -0.07
    Tai
    -0.07
    沿
    -0.07
    POSITIVE LOGITS
     cuisine
    0.12
     Cuisine
    0.11
     cuis
    0.10
    ourn
    0.07
     conven
    0.07
     Cinema
    0.07
     criteria
    0.07
     uży
    0.07
    UDA
    0.07
    endereco
    0.07
    Act Density 0.005%

    No Known Activations