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

    Neuronpedia

    INDEX
    Explanations

    chances

    np_max-act · gemini-2.0-flash

    This neuron spots numeric tokens—especially decimal values and other numbers—wherever they appear in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     イ
    -0.07
     晴
    -0.07
     imdb
    -0.07
     spect
    -0.06
     Blackburn
    -0.06
     labyrinth
    -0.06
    )||(
    -0.06
     reported
    -0.06
     مردم
    -0.06
     Awakening
    -0.06
    POSITIVE LOGITS
    ãy
    0.06
    /e
    0.06
     spacer
    0.06
    (await
    0.06
    ское
    0.06
    untary
    0.06
    TJ
    0.06
    von
    0.06
    .datasource
    0.06
    днання
    0.06
    Act Density 0.658%

    No Known Activations