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

    Neuronpedia

    INDEX
    Explanations

    teaspoon

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens indicating ingredient quantity measurements (e.g., “cup,” “tablespoon,” “teaspoon”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     filmmaker
    -0.07
     CircularProgressIndicator
    -0.07
    хов
    -0.07
    ographic
    -0.06
     Aydın
    -0.06
     pigs
    -0.06
    semblies
    -0.06
    ocular
    -0.06
    ��
    -0.06
    @
    -0.06
    POSITIVE LOGITS
     scientist
    0.07
     Stephan
    0.07
     Toys
    0.07
    .ComponentModel
    0.06
     extravagant
    0.06
     tsp
    0.06
     teaspoon
    0.06
    reaction
    0.06
    []{"
    0.06
     وأن
    0.06
    Act Density 0.006%

    No Known Activations