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

    Neuronpedia

    INDEX
    Explanations

    Item descriptions

    np_max-act · gemini-2.0-flash

    This neuron fires on quoted product or item titles, highlighting the text enclosed in quotation marks that names the item.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Enumerable
    -0.07
     ul
    -0.07
    uled
    -0.06
    ulp
    -0.06
     UUID
    -0.06
    `;↵
    -0.06
     substring
    -0.06
     noct
    -0.06
     Über
    -0.06
     inputStream
    -0.06
    POSITIVE LOGITS
    ινή
    0.07
    ulkan
    0.06
     ödeme
    0.06
    .blob
    0.06
    یمت
    0.06
    فن
    0.06
     timber
    0.06
     Honestly
    0.06
    rostřed
    0.06
     opposing
    0.06
    Act Density 0.026%

    No Known Activations