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

    Neuronpedia

    INDEX
    Explanations

    Recipes

    np_max-act · gemini-2.0-flash

    This neuron detects Spanish cooking‐recipe section headings or keywords (e.g. “receta,” “ingredientes,” “preparación”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    tones
    -0.07
    URRED
    -0.07
     neighb
    -0.07
    enties
    -0.06
     pioneered
    -0.06
    agina
    -0.06
    病
    -0.06
    학년
    -0.06
    .Fields
    -0.06
    _tensors
    -0.06
    POSITIVE LOGITS
     clean
    0.06
     oath
    0.06
    Pre
    0.06
     Duch
    0.06
    acket
    0.06
    /example
    0.06
    ._
    0.06
     воды
    0.06
    pell
    0.06
    texture
    0.06
    Act Density 0.025%

    No Known Activations