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

    Neuronpedia

    INDEX
    Explanations

    instructions, advice

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect numbered list markers (e.g. the “1.”, “2.”, etc., and their accompanying punctuation) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     rubbing
    -0.07
     未
    -0.07
     Natal
    -0.07
    岁
    -0.06
    出版社
    -0.06
     आन
    -0.06
     již
    -0.06
    دانلود
    -0.06
     非
    -0.06
    符合
    -0.06
    POSITIVE LOGITS
    =[
    0.07
    Plus
    0.06
    !!!
    0.06
    ////////
    0.06
    errorMessage
    0.06
    urgeon
    0.06
    =c
    0.06
    _hr
    0.06
    ervisor
    0.06
    ايا
    0.06
    Act Density 0.043%

    No Known Activations