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 activates on words that describe food‐prep actions (e.g., “cut,” “chopped,” “crushed,” “rinsed”) in cooking instructions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     signalling
    -0.07
    armacy
    -0.07
    .rooms
    -0.07
     curing
    -0.07
     محدود
    -0.06
     CGRectGet
    -0.06
    anism
    -0.06
     renal
    -0.06
    ованих
    -0.06
    —is
    -0.06
    POSITIVE LOGITS
     totally
    0.08
     كور
    0.07
     waiting
    0.06
     तरह
    0.06
    	cr
    0.06
    908
    0.06
    poz
    0.06
     derece
    0.06
     really
    0.06
     accustomed
    0.06
    Act Density 0.006%

    No Known Activations