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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash

    This neuron fires on personal pronouns—especially direct second-person and third-person forms like “you,” “him,” “she,” etc.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    符合
    -0.07
     Systems
    -0.07
     upto
    -0.07
     genocide
    -0.06
    ５
    -0.06
     Ree
    -0.06
    ￣￣
    -0.06
    าเล
    -0.06
    Separ
    -0.06
    prestashop
    -0.06
    POSITIVE LOGITS
    ДА
    0.06
     marital
    0.06
     altering
    0.06
    صر
    0.06
    ([
↵
    0.06
     trolls
    0.06
    .then
    0.06
     úč
    0.06
    /Q
    0.06
    -я
    0.06
    Act Density 0.159%

    No Known Activations