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

    Neuronpedia

    INDEX
    Explanations

    chemistry/physics abstracts

    np_max-act · gemini-2.0-flash

    This neuron detects tokens that are part of chemical formulas or material compositions, specifically element symbols paired with numerical values or subscripts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     fare
    -0.06
    172
    -0.06
    719
    -0.06
     rede
    -0.06
    amentals
    -0.06
    kom
    -0.06
    осудар
    -0.06
    -y
    -0.06
     lear
    -0.06
    ocomplete
    -0.06
    POSITIVE LOGITS
    (Func
    0.06
     Tehran
    0.06
     AA
    0.06
    _WEIGHT
    0.06
     Temmuz
    0.06
    sthrough
    0.06
    Assignment
    0.06
     secara
    0.06
     THR
    0.06
     확인
    0.06
    Act Density 0.004%

    No Known Activations