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

    Neuronpedia

    INDEX
    Explanations

    Mathematical notation

    np_max-act · gemini-2.0-flash

    This neuron fires on mathematical formula tokens—especially commutators, field‐strength tensors, and gauge‐transformation expressions in TeX/LaTeX math notation.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     director
    -0.07
     detention
    -0.07
     Director
    -0.07
     point
    -0.07
    director
    -0.07
    455
    -0.06
    *((
    -0.06
    िथ
    -0.06
    üyordu
    -0.06
     Point
    -0.06
    POSITIVE LOGITS
     SSL
    0.07
     keyst
    0.07
     mitt
    0.06
     buffered
    0.06
     uvědom
    0.06
     charging
    0.06
     çevres
    0.06
     nez
    0.06
     sorter
    0.06
     svenska
    0.06
    Act Density 0.002%

    No Known Activations