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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    standard recipes for cooking chicken.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on imperative cooking-step phrases—especially “Remove the …” instructions in recipes.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     DR
    -0.07
    _gallery
    -0.06
     Spirits
    -0.06
    .prev
    -0.06
     Sell
    -0.06
    杯
    -0.06
    	Me
    -0.06
     fld
    -0.06
     commitments
    -0.06
    Motor
    -0.06
    POSITIVE LOGITS
    bat
    0.07
     over
    0.06
    arend
    0.06
     quả
    0.06
    -over
    0.06
     Vietnamese
    0.06
     pageInfo
    0.06
     những
    0.06
     понять
    0.06
    0.06
    Act Density 0.011%

    No Known Activations