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

    Neuronpedia

    INDEX
    Explanations

    forum posts

    np_max-act · gemini-2.0-flash

    The neuron fires on structural or formatting tokens in the prompt—things like section headers, numbered list markers, and other metadata/markup elements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .ArgumentParser
    -0.07
    頁
    -0.06
    듯
    -0.06
    peated
    -0.06
    .logical
    -0.06
    heads
    -0.06
    fra
    -0.06
    	Run
    -0.06
     Рег
    -0.06
     dispro
    -0.06
    POSITIVE LOGITS
    *width
    0.06
     무엇
    0.06
     LOOK
    0.06
    ',
↵
    0.06
     buttonWithType
    0.06
     nouvel
    0.06
    _LIB
    0.06
     몽
    0.06
    =models
    0.06
     Caesar
    0.06
    Act Density 0.053%

    No Known Activations