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

    Neuronpedia

    INDEX
    Explanations

    students/pupils

    np_max-act · gemini-2.0-flash

    educational institutions and their historical background.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on numeric and quantitative expressions—counts, statistics, and other number-related tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     baths
    -0.07
     contained
    -0.06
    iaux
    -0.06
    mental
    -0.06
    겼
    -0.06
    ،↵
    -0.06
    −
    -0.06
     DVDs
    -0.06
    (SC
    -0.06
    _body
    -0.06
    POSITIVE LOGITS
     لك
    0.07
    {}".
    0.07
     datab
    0.07
    ินทร
    0.06
     valores
    0.06
     pří
    0.06
     dorm
    0.06
     sendo
    0.06
     thriving
    0.06
     чи
    0.06
    Act Density 0.015%

    No Known Activations