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 numeric literals (numbers, decimals, and unit values) in code, especially CSS dimension or percentage values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     UPDATED
    -0.07
     Nut
    -0.07
     Pruitt
    -0.06
     film
    -0.06
    》的
    -0.06
     Loot
    -0.06
     Davis
    -0.06
    것
    -0.06
    Davis
    -0.06
     Mus
    -0.06
    POSITIVE LOGITS
    flamm
    0.07
    'im
    0.06
    .liferay
    0.06
     uygun
    0.06
    Sections
    0.06
    ***/↵↵
    0.06
     домаш
    0.06
    .chk
    0.06
    /use
    0.06
    UPER
    0.06
    Act Density 0.003%

    No Known Activations