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

    Neuronpedia

    INDEX
    Explanations

    flavor

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the word “flavor” (or its British spelling “flavour”) in text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     rit
    -0.07
    "math
    -0.07
    _send
    -0.07
    िध
    -0.07
    .Node
    -0.07
     Checklist
    -0.07
     เช
    -0.07
    GMT
    -0.06
     satellite
    -0.06
     března
    -0.06
    POSITIVE LOGITS
     flavor
    0.14
     Flavor
    0.10
     flavored
    0.10
     flavour
    0.10
     flavors
    0.10
     flavours
    0.09
     flaw
    0.08
    avor
    0.08
    -gr
    0.07
    AVOR
    0.07
    Act Density 0.006%

    No Known Activations