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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric tokens—especially decimal numbers and other numerical values embedded in formulae.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    completed
    -0.07
    mana
    -0.07
    domains
    -0.07
    Msp
    -0.06
     carried
    -0.06
     vhodné
    -0.06
     possesses
    -0.06
    ml
    -0.06
    months
    -0.06
     couldn
    -0.06
    POSITIVE LOGITS
    .ColumnName
    0.07
    秦
    0.06
     Champagne
    0.06
     Navy
    0.06
    .setWindowTitle
    0.06
    (:,
    0.06
    omal
    0.06
     $('#'
    0.06
     SCI
    0.06
     xAxis
    0.06
    Act Density 0.027%

    No Known Activations