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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    This neuron detects decimal numbers (floating‐point numeric tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Winds
    -0.06
     Sunny
    -0.06
     productService
    -0.06
     안전
    -0.06
     Dark
    -0.06
    ,',
    -0.06
    Funny
    -0.06
     dark
    -0.06
    Dark
    -0.06
    zon
    -0.06
    POSITIVE LOGITS
    аторы
    0.06
    prising
    0.06
    ===↵
    0.06
    ох
    0.06
     epilepsy
    0.06
     notifies
    0.06
    чої
    0.06
    locked
    0.06
    ого
    0.06
     encount
    0.06
    Act Density 0.002%

    No Known Activations