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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    the start of assistant responses, especially generic preamble/introductory phrasing that signals an answer is beginning.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    anson
    -0.07
     мног
    -0.06
     psy
    -0.06
    anye
    -0.06
     coastline
    -0.06
    =this
    -0.06
     exploits
    -0.06
    _SETTING
    -0.05
     confidence
    -0.05
    apps
    -0.05
    POSITIVE LOGITS
    ��
    0.07
     iletişim
    0.07
    (sk
    0.06
    적인
    0.06
     '..
    0.06
     backButton
    0.06
    님의
    0.06
     trái
    0.06
    .wordpress
    0.06
    CollectionView
    0.06
    Act Density 0.078%

    No Known Activations