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

    Neuronpedia

    INDEX
    Explanations

    Dates around 2010-2020

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric tokens—especially year-like or other multi‐digit number strings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .subject
    -0.07
    /
↵
    -0.06
    xAC
    -0.06
    ลาย
    -0.06
    MI
    -0.06
    нож
    -0.06
    CreatedBy
    -0.06
    \Tests
    -0.06
    .Asset
    -0.06
    روز
    -0.06
    POSITIVE LOGITS
     rumor
    0.06
     __________________________________
    0.06
    atur
    0.06
    ================
    0.06
    _beam
    0.06
    201
    0.06
     retain
    0.06
     볼
    0.06
     pallet
    0.06
     incr
    0.06
    Act Density 0.097%

    No Known Activations