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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    This neuron detects numeric data—especially decimals, percentages, and other statistical figures—in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sau
    -0.06
     encore
    -0.06
     Pasta
    -0.06
    ITIZE
    -0.06
     Shark
    -0.06
     pets
    -0.06
    _HINT
    -0.06
     debated
    -0.06
    ampil
    -0.06
    leo
    -0.06
    POSITIVE LOGITS
    事件
    0.07
    inputEmail
    0.07
    ellation
    0.07
     hilar
    0.06
    伙
    0.06
    θη
    0.06
     власності
    0.06
    getIndex
    0.06
     converters
    0.06
    对方
    0.06
    Act Density 0.014%

    No Known Activations