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

    Neuronpedia

    INDEX
    Explanations

    Fibonacci

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of the Fibonacci sequence, i.e. the word “Fibonacci” (and its tokenized parts).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    BD
    -0.07
    izzard
    -0.07
    loon
    -0.06
    Wed
    -0.06
    OND
    -0.06
     Hod
    -0.06
     Duch
    -0.06
    cly
    -0.06
     Judges
    -0.06
     Kel
    -0.06
    POSITIVE LOGITS
    淡
    0.07
    无码
    0.07
     Momentum
    0.07
    ใกล
    0.07
     ListNode
    0.07
     dotenv
    0.06
     potassium
    0.06
     mary
    0.06
     libido
    0.06
    (comm
    0.06
    Act Density 0.002%

    No Known Activations