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

    Neuronpedia

    INDEX
    Explanations

    Random text snippets

    np_max-act · gemini-2.0-flash

    This neuron fires on section headings or document title lines (short, title-cased phrases set off as headings).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     interpreting
    -0.07
    .protobuf
    -0.06
     застав
    -0.06
    cstdint
    -0.06
    ocused
    -0.06
    ací
    -0.06
    _TARGET
    -0.06
    metry
    -0.06
     попыт
    -0.06
    GG
    -0.06
    POSITIVE LOGITS
    指定
    0.07
    "</
    0.07
     Latinos
    0.07
     sleeps
    0.06
    promotion
    0.06
    _best
    0.06
     všem
    0.06
    ¿
    0.06
     clever
    0.06
    ～～
    0.06
    Act Density 0.009%

    No Known Activations