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

    Neuronpedia

    INDEX
    Explanations

    Physics/scientific equations

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens that are part of mathematical expressions or LaTeX‐style notation (e.g. operators, subscripts, superscripts, sums, fractions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    MAT
    -0.07
     Shopify
    -0.07
    ."""↵
    -0.07
     Tus
    -0.07
     measurable
    -0.07
     Anglo
    -0.06
    ?(:
    -0.06
    andard
    -0.06
     IO
    -0.06
     Standard
    -0.06
    POSITIVE LOGITS
    ARRY
    0.07
     Peter
    0.07
    Peter
    0.07
    .IsSuccess
    0.06
     nitel
    0.06
     sorun
    0.06
    ình
    0.06
     соот
    0.06
    der
    0.06
    .createElement
    0.06
    Act Density 0.002%

    No Known Activations