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

    Neuronpedia

    INDEX
    Explanations

    School year

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens and quantitative statistics (e.g. numbers, decimals, percentages) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     neuronal
    -0.06
     Newest
    -0.06
    .list
    -0.06
     DG
    -0.06
     assembled
    -0.06
     прибор
    -0.06
     заверш
    -0.06
     sorted
    -0.06
     descriptions
    -0.06
     Composition
    -0.06
    POSITIVE LOGITS
    '].$
    0.07
    学院
    0.07
     usize
    0.07
    ?=
    0.06
    喜
    0.06
     مانند
    0.06
    283
    0.06
    ονται
    0.06
    ُع
    0.06
    ライ
    0.06
    Act Density 0.008%

    No Known Activations