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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens that are part of mathematical notation or formulas—numbers, operators, and variable/expression syntax.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     brag
    -0.07
     bağır
    -0.06
    лиц
    -0.06
    ิล
    -0.06
    -cell
    -0.06
     côt
    -0.06
    _para
    -0.06
     Coding
    -0.06
     Dyn
    -0.06
    ิตร
    -0.06
    POSITIVE LOGITS
    […
    0.06
    .toCharArray
    0.06
     Forecast
    0.06
     Palest
    0.06
    TM
    0.06
     IDF
    0.06
     شكل
    0.06
     period
    0.06
    suma
    0.06
    olecule
    0.06
    Act Density 0.011%

    No Known Activations