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

    Neuronpedia

    INDEX
    Explanations

    lt

    np_max-act · gemini-2.0-flash

    This neuron fires on HTML/XML markup elements (e.g. tag delimiters like “<”, “>” and entity escapes such as “&lt;”/“&gt;”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Howe
    -0.07
    -dev
    -0.07
    凌
    -0.06
    ippines
    -0.06
     catastrophic
    -0.06
     обов
    -0.06
     кост
    -0.06
    obre
    -0.06
    )prepareForSegue
    -0.06
    브
    -0.06
    POSITIVE LOGITS
     geile
    0.07
     <
    0.07
    driver
    0.06
    탄
    0.06
    詞
    0.06
     lab
    0.06
       
↵
    0.06
    .ls
    0.06
     <?
    0.06
     Command
    0.06
    Act Density 0.002%

    No Known Activations