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

    Neuronpedia

    INDEX
    Explanations

    cooking instructions

    np_max-act · gemini-2.0-flash

    The neuron fires on cooking‐procedure verbs (especially present‐tense imperatives like “stir,” “fry,” “cook,” “simmer,” etc.) in recipe instructions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Athen
    -0.06
     criteria
    -0.06
    greens
    -0.06
    ひと
    -0.06
    _Printf
    -0.06
     Lem
    -0.06
    vět
    -0.06
     одном
    -0.06
    FFT
    -0.06
     가격
    -0.06
    POSITIVE LOGITS
     bt
    0.07
     '/')↵
    0.07
    ,))↵
    0.06
    pedia
    0.06
    baz
    0.06
    (tuple
    0.06
    ريس
    0.06
    .hostname
    0.06
    Dec
    0.06
    ائز
    0.06
    Act Density 0.010%

    No Known Activations