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 activates on numeric and mathematical tokens (digits, decimal numbers, and LaTeX math elements) inside equations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _Ptr
    -0.07
     QDir
    -0.07
     kar
    -0.07
    _vk
    -0.07
     DLL
    -0.06
    _TWO
    -0.06
    AFF
    -0.06
    (Optional
    -0.06
    _recursive
    -0.06
    -oriented
    -0.06
    POSITIVE LOGITS
    다고
    0.08
     고
    0.07
    =""></
    0.07
     nghiệ
    0.06
    是
    0.06
     шт
    0.06
    л
    0.06
     create
    0.06
    톡
    0.06
     queda
    0.06
    Act Density 0.028%

    No Known Activations