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

    Neuronpedia

    INDEX
    Explanations

    ed

    np_max-act · gemini-2.0-flash

    The neuron is specialized to detect numeric fragments from floating‐point values (decimal fractions) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    �
    -0.07
    _LIST
    -0.06
     uphe
    -0.06
     Architecture
    -0.06
    contracts
    -0.06
     речі
    -0.06
     libro
    -0.06
    иту
    -0.06
     cms
    -0.06
    .Th
    -0.05
    POSITIVE LOGITS
    abay
    0.07
     ویژ
    0.07
     Jamal
    0.06
     ┃
    0.06
    (UUID
    0.06
    (Func
    0.06
    .isLoading
    0.06
     chants
    0.06
    _COLLECTION
    0.06
     Japon
    0.06
    Act Density 0.034%

    No Known Activations