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

    Neuronpedia

    INDEX
    Explanations

    colon character

    np_max-act · gemini-2.0-flash

    The neuron consistently fires on the “:” token, i.e. it detects colon punctuation.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _market
    -0.07
     topping
    -0.06
     proteins
    -0.06
    베
    -0.06
     backend
    -0.06
     Pir
    -0.06
    Testing
    -0.06
    bef
    -0.06
    disabled
    -0.06
    ποί
    -0.06
    POSITIVE LOGITS
     [~,
    0.06
     जन
    0.06
    \GeneratedValue
    0.06
    (jQuery
    0.06
    bruar
    0.06
     "&#
    0.06
    .pol
    0.06
    BundleOrNil
    0.06
     полит
    0.06
    .metric
    0.06
    Act Density 0.002%

    No Known Activations