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

    Neuronpedia

    INDEX
    Explanations

    font

    np_max-act · gemini-2.0-flash

    The neuron detects HTML markup tags used for visual styling (e.g. <font> and <b> tags).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Lag
    -0.07
    #ga
    -0.06
     lag
    -0.06
    uku
    -0.06
     bureauc
    -0.06
    km
    -0.06
     traumatic
    -0.06
     enthusiasm
    -0.06
     teaspoons
    -0.06
    Located
    -0.06
    POSITIVE LOGITS
     一般
    0.07
    .Localization
    0.07
    éments
    0.07
    Н
    0.07
    (n
    0.06
    ováno
    0.06
    _COLORS
    0.06
    …ط
    0.06
    보다
    0.06
    (serializers
    0.06
    Act Density 0.001%

    No Known Activations