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

    Neuronpedia

    INDEX
    Explanations

    cooking recipes

    np_max-act · gemini-2.0-flash

    The neuron fires on imperative cooking‐action verbs (e.g. Preheat, Grease, Beat, Stir, Fold, Bake) that begin recipe instruction steps.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     دنی
    -0.07
    /navigation
    -0.06
     teşkil
    -0.06
    whereIn
    -0.06
     аль
    -0.06
    ้อง
    -0.06
     Gle
    -0.06
     Něm
    -0.06
    pres
    -0.06
    Saint
    -0.06
    POSITIVE LOGITS
    "--
    0.07
    $↵
    0.07
    *(
    0.06
    .inspect
    0.06
    σμο
    0.06
    "]]
    0.06
    }`}
    0.06
    _stub
    0.06
     shortcuts
    0.06
     Superv
    0.06
    Act Density 0.015%

    No Known Activations