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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash

    The neuron activates on numerical measurement tokens (e.g. decimal numbers, values with units) in scientific text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     clubhouse
    -0.07
    jan
    -0.07
    eru
    -0.07
    -shot
    -0.06
    cak
    -0.06
    -t
    -0.06
     suicidal
    -0.06
     mushrooms
    -0.06
     abolition
    -0.06
    erot
    -0.06
    POSITIVE LOGITS
    [Boolean
    0.07
     메
    0.07
    */
↵
↵
    0.07
    蘭
    0.06
     letzten
    0.06
     Bugün
    0.06
     CSP
    0.06
    (chain
    0.06
     {{--<
    0.06
               
↵
    0.06
    Act Density 0.076%

    No Known Activations