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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric‐style tokens—especially measurement values and decimals in scientific data.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     pellet
    -0.07
    上的
    -0.06
     Besides
    -0.06
    ç
    -0.06
     quantum
    -0.06
    」の
    -0.06
    усти
    -0.06
     Adobe
    -0.06
     Infos
    -0.05
     thầu
    -0.05
    POSITIVE LOGITS
     ano
    0.07
    TextWriter
    0.07
    bindParam
    0.06
    市
    0.06
    Trees
    0.06
    .nextInt
    0.06
    写
    0.06
     happens
    0.06
     wardrobe
    0.06
    Friend
    0.06
    Act Density 0.343%

    No Known Activations