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

    Neuronpedia

    INDEX
    Explanations

    reflex

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “reflex” (including variants like H-reflex) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    صت
    -0.07
    }),↵
    -0.07
     حمایت
    -0.07
    �
    -0.07
    —not
    -0.07
    _dur
    -0.07
    ImagePath
    -0.07
     budou
    -0.07
     накоп
    -0.07
    Sand
    -0.07
    POSITIVE LOGITS
     reflex
    0.11
     Reflex
    0.11
    _Base
    0.07
    oggle
    0.07
    okable
    0.07
     عکس
    0.07
     Josef
    0.07
    Recipes
    0.07
    echo
    0.06
    base
    0.06
    Act Density 0.002%

    No Known Activations