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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash

    The neuron chiefly picks out mathematical notation tokens—variables, symbols, numbers, and LaTeX/math‐mode constructs.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    book
    -0.06
    _pan
    -0.06
     proceeding
    -0.06
    _atual
    -0.06
    範
    -0.06
    fill
    -0.06
    shown
    -0.06
    ษ
    -0.06
    がある
    -0.06
     Якщо
    -0.06
    POSITIVE LOGITS
     ülkemiz
    0.07
     Mehr
    0.06
     stigma
    0.06
    organic
    0.06
     entwick
    0.06
    ))).
    0.06
     coupling
    0.06
     Placement
    0.06
     VP
    0.06
     maternal
    0.06
    Act Density 0.174%

    No Known Activations