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

    Neuronpedia

    INDEX
    Explanations

    polymers

    np_max-act · gemini-2.0-flash

    This neuron detects references to polymer chemistry terminology, especially names of monomer/polymer building blocks (e.g., ethylene, monomer, polymer, copolymer, ether).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ポ
    -0.07
    cctor
    -0.06
    _mar
    -0.06
    adem
    -0.06
    �n
    -0.06
     מ
    -0.06
     مور
    -0.06
    <*
    -0.06
    ★★
    -0.06
     especific
    -0.06
    POSITIVE LOGITS
     пад
    0.07
     tiếp
    0.07
     assess
    0.07
    .syntax
    0.06
     getting
    0.06
     مرح
    0.06
     catching
    0.06
    بول
    0.06
    .cvtColor
    0.06
     Tổng
    0.06
    Act Density 0.020%

    No Known Activations