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

    Neuronpedia

    INDEX
    Explanations

    auto

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literal tokens (especially fractional numbers and units) in CSS code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     پاد
    -0.07
    _intensity
    -0.06
     Pemb
    -0.06
     Geb
    -0.06
     mulheres
    -0.06
     Sở
    -0.06
    ��
    -0.06
     statt
    -0.06
    ermalink
    -0.06
    (Bundle
    -0.06
    POSITIVE LOGITS
    Author
    0.07
    otty
    0.07
     ger
    0.07
    runner
    0.06
    ytt
    0.06
    vector
    0.06
    /read
    0.06
     чемпион
    0.06
    .Real
    0.06
     tenure
    0.06
    Act Density 0.001%

    No Known Activations