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

    Neuronpedia

    INDEX
    Explanations

    Lagrangian (physics, math)

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the word “Lagrangian” (and closely related forms) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    }):
    -0.07
     municipal
    -0.07
    NEL
    -0.07
     Carousel
    -0.06
    -field
    -0.06
    建設
    -0.06
     nuclear
    -0.06
    _ds
    -0.06
     Discover
    -0.06
     compreh
    -0.06
    POSITIVE LOGITS
    ABSPATH
    0.07
    rang
    0.07
    _LR
    0.06
     Cleans
    0.06
     中
    0.06
    walking
    0.06
    ρωση
    0.06
     [=[
    0.06
    няется
    0.06
     trang
    0.06
    Act Density 0.002%

    No Known Activations