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

    Neuronpedia

    INDEX
    Explanations

    &

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric tokens, especially decimal‐point numbers (floating‐point literals).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    439
    -0.08
     fingers
    -0.07
    shot
    -0.06
    /lo
    -0.06
     plate
    -0.06
     digestive
    -0.06
     verg
    -0.06
    وئ
    -0.06
    олі
    -0.06
     tense
    -0.06
    POSITIVE LOGITS
    /classes
    0.07
     Contrib
    0.06
     Pand
    0.06
    ansson
    0.06
     Non
    0.06
     unfair
    0.06
     yıllar
    0.06
     expectancy
    0.06
     NSArray
    0.06
     asym
    0.06
    Act Density 0.003%

    No Known Activations