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

    Neuronpedia

    INDEX
    Explanations

    file metadata

    np_max-act · gemini-2.0-flash

    The neuron is looking for publication metadata, especially date and time stamps (and related labels) in the document.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    試
    -0.07
     مثال
    -0.06
    "g
    -0.06
     december
    -0.06
     LGBTQ
    -0.06
     옷
    -0.06
     mill
    -0.06
     cellar
    -0.06
     perfection
    -0.06
    Api
    -0.06
    POSITIVE LOGITS
    /by
    0.07
    _SS
    0.07
     tweeted
    0.07
    تس
    0.07
     Hussein
    0.06
    entity
    0.06
    unfinished
    0.06
     eject
    0.06
    jourd
    0.06
    _PUSHDATA
    0.06
    Act Density 0.006%

    No Known Activations