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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    The neuron fires on standalone numeric tokens—particularly those denoting years, volume/page numbers, and other citation‐style numerals.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    уч
    -0.07
    _lc
    -0.07
     alt
    -0.07
    accumulate
    -0.07
    _SOURCE
    -0.07
     رشد
    -0.06
     hare
    -0.06
     모두
    -0.06
     tín
    -0.06
    Reading
    -0.06
    POSITIVE LOGITS
     Put
    0.07
    خاب
    0.06
    يار
    0.06
     WP
    0.06
     righteous
    0.06
    nection
    0.06
    metics
    0.06
     tattoo
    0.06
    ини
    0.06
    ительные
    0.06
    Act Density 0.014%

    No Known Activations