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

    Neuronpedia

    INDEX
    Explanations

    scientific measurements

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens—especially decimal numbers and measurement values in scientific contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ulant
    -0.07
     congestion
    -0.06
    olson
    -0.06
     Final
    -0.06
     Shadows
    -0.06
    anine
    -0.06
     Revel
    -0.06
    (\"
    -0.06
     }])↵
    -0.06
     ATK
    -0.06
    POSITIVE LOGITS
    ecom
    0.07
     rogue
    0.06
     bombings
    0.06
     вов
    0.06
     colorWith
    0.06
    295
    0.06
    ($_
    0.06
    Land
    0.06
    rgba
    0.06
     Land
    0.06
    Act Density 0.012%

    No Known Activations