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

    Neuronpedia

    INDEX
    Explanations

    ingredients, cooking methods, and preparation steps related to recipes

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

    cooking or cooked meat

    np_acts-logits-general · gemini-2.0-flash

    cooking doneness and quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EnableWeb
    -0.51
     désolés
    -0.50
    dova
    -0.49
    éras
    -0.49
    WithIOException
    -0.47
    colato
    -0.46
    hasNext
    -0.45
    ArgumentParser
    -0.45
    liquez
    -0.45
    utches
    -0.45
    POSITIVE LOGITS
     cuisson
    0.70
     cooked
    0.69
    Rare
    0.67
     Rare
    0.67
     estekak
    0.67
     charred
    0.66
    cooked
    0.65
     rare
    0.64
    rare
    0.63
     cottura
    0.63
    Act Density 0.090%

    No Known Activations