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

    Neuronpedia

    INDEX
    Explanations

    founded

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens in “History” or founding sentences—especially around words like “History,” “It was founded in,” and associated dates—i.e. it spots establishment/founding information.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ntag
    -0.07
    ümüz
    -0.06
    -band
    -0.06
    /document
    -0.06
     Binding
    -0.06
    ázky
    -0.06
     unborn
    -0.06
    .Ui
    -0.06
    .nativeElement
    -0.06
    -language
    -0.06
    POSITIVE LOGITS
    getitem
    0.06
    壓
    0.06
     Presents
    0.06
    dirname
    0.06
    ukkit
    0.06
     squeeze
    0.06
    олева
    0.06
    Vel
    0.06
    ไซ
    0.06
     sàng
    0.06
    Act Density 0.030%

    No Known Activations