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

    Neuronpedia

    INDEX
    Explanations

    Math calculations

    np_max-act · gemini-2.0-flash

    The neuron is triggered by numeric expressions in math‐problem contexts—especially sequences of integers, fractions, and arithmetic terms (e.g. common denominators, multiples, divisors).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .sendFile
    -0.09
     ؟
    -0.07
    geois
    -0.07
    átek
    -0.07
    يلا
    -0.06
    /vendor
    -0.06
     mænd
    -0.06
    newInstance
    -0.06
     POD
    -0.06
    tım
    -0.06
    POSITIVE LOGITS
     provid
    0.06
    urning
    0.06
     pays
    0.06
     větš
    0.06
    ้อ
    0.06
    ';↵↵↵
    0.06
     пре
    0.06
     pr
    0.06
     مدیریت
    0.06
    Ale
    0.06
    Act Density 0.057%

    No Known Activations