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

    Neuronpedia

    INDEX
    Explanations

    Cooking and recipes

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect words referring to cooking actions or techniques.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     rotation
    -0.08
     flight
    -0.07
    .Box
    -0.06
     geometric
    -0.06
    CEPTION
    -0.06
     раз
    -0.06
     hijos
    -0.06
     myst
    -0.06
     donations
    -0.06
     drink
    -0.06
    POSITIVE LOGITS
    енты
    0.07
    qty
    0.07
    )b
    0.06
    ẳn
    0.06
    loub
    0.06
    assert
    0.06
     Addresses
    0.06
    obsolete
    0.06
     "#{
    0.06
    Feels
    0.06
    Act Density 0.047%

    No Known Activations