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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    punctuation that marks sentence or clause boundaries, especially end-of-sentence marks.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    amientos
    -0.07
     ect
    -0.07
     door
    -0.07
     стол
    -0.07
    �
    -0.07
    咡
    -0.06
    ización
    -0.06
     approves
    -0.06
     elections
    -0.06
    ﻵ
    -0.06
    POSITIVE LOGITS
    .den
    0.07
    克思
    0.07
     Orleans
    0.07
     сайт
    0.07
     Ferdinand
    0.07
     !==
    0.07
    .Frame
    0.07
     thats
    0.06
    Were
    0.06
    鼓舞
    0.06
    Act Density 1.088%

    No Known Activations