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

    Neuronpedia

    INDEX
    Explanations

    academic writing

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is spot numerical/statistical expressions (numbers, percentages, p-values, confidence intervals, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Widget
    -0.07
     gigantic
    -0.07
    (dispatch
    -0.07
     swaps
    -0.07
     éc
    -0.07
    yyyyMMdd
    -0.06
    jpg
    -0.06
     Convers
    -0.06
    Mad
    -0.06
     печ
    -0.06
    POSITIVE LOGITS
    duğ
    0.06
    .FirstOrDefault
    0.06
    lov
    0.06
    loo
    0.06
    datum
    0.06
    gard
    0.06
    sled
    0.06
     بای
    0.06
    pecial
    0.06
    sk
    0.06
    Act Density 0.055%

    No Known Activations