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

    Neuronpedia

    INDEX
    Explanations

    Blog posts/articles

    np_max-act · gemini-2.0-flash

    This neuron specializes in spotting words that are part of article or blog‐post titles and headings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    azer
    -0.08
    маг
    -0.07
     mighty
    -0.06
     تعمیر
    -0.06
     Пред
    -0.06
    케
    -0.06
     Levin
    -0.06
     nuts
    -0.06
    /book
    -0.06
    z
    -0.06
    POSITIVE LOGITS
    .IsFalse
    0.06
     defaultMessage
    0.06
    σσότε
    0.06
    ifdef
    0.06
     OSD
    0.06
     applied
    0.06
     HttpServletRequest
    0.06
    #ifdef
    0.06
     забезпеч
    0.06
     eliminar
    0.06
    Act Density 0.049%

    No Known Activations