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 activates on LaTeX/math notation tokens (e.g. “$”, mathcal/mathbb commands, Greek letters, and other formula symbols).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ivation
    -0.07
     onView
    -0.07
     shiny
    -0.07
     clone
    -0.07
     Stars
    -0.07
    survey
    -0.07
     bump
    -0.06
     summarizes
    -0.06
     initiate
    -0.06
     ****************************************************************************
    -0.06
    POSITIVE LOGITS
    κει
    0.07
     tôn
    0.06
    .isDebugEnabled
    0.06
     Lance
    0.06
    аль
    0.06
    Href
    0.06
    ديد
    0.06
    ennifer
    0.06
    ulls
    0.06
     cellForRowAtIndexPath
    0.06
    Act Density 0.016%

    No Known Activations