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

    Neuronpedia

    INDEX
    Explanations

    gauge

    np_max-act · gemini-2.0-flash

    The neuron is tuned to detect references to gauge theory terminology (e.g. “gauge,” “gauge field,” “gauge symmetry”) in physics texts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     mixins
    -0.06
     besides
    -0.06
     Tibetan
    -0.06
    传
    -0.06
    plotlib
    -0.06
    �
    -0.06
     Vy
    -0.06
    คำ
    -0.06
     thịt
    -0.06
     Loren
    -0.06
    POSITIVE LOGITS
     gauge
    0.07
    ookie
    0.07
     haut
    0.06
    VisualStyle
    0.06
    QS
    0.06
    Gar
    0.06
     gaming
    0.06
     Shame
    0.06
    іки
    0.06
       ↵
    0.06
    Act Density 0.001%

    No Known Activations