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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash

    HTML tags and web page structure elements.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects floating‐point numeric values in HTML tag attributes (e.g., frameborder, scrolling, width/height decimals).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Swords
    -0.07
     Phrase
    -0.07
    (Me
    -0.07
    _TREE
    -0.06
     phenomenal
    -0.06
    Retail
    -0.06
     controlled
    -0.06
     Medium
    -0.06
     advocating
    -0.06
    .TextBox
    -0.06
    POSITIVE LOGITS
     również
    0.08
    <Transform
    0.06
    Jessica
    0.06
     panorama
    0.06
    ざ
    0.06
    generator
    0.06
    """),↵
    0.06
    рива
    0.06
    開始
    0.06
     bere
    0.06
    Act Density 0.001%

    No Known Activations