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

    Neuronpedia

    INDEX
    Explanations

    Using

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the verb “Using” (typically at the start of a clause) when describing methodological steps.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    prd
    -0.07
    ',

↵
    -0.07
    antd
    -0.07
    .hadoop
    -0.07
     Welcome
    -0.07
    /legal
    -0.07
    aec
    -0.07
     policym
    -0.06
    ZW
    -0.06
     Creed
    -0.06
    POSITIVE LOGITS
    */↵
    0.06
    !’
    0.06
      ↵
    0.06
     <>↵
    0.06
    "]↵
    0.06
    (location
    0.06
     chia
    0.06
     Pipeline
    0.06
     更新
    0.06
    availability
    0.06
    Act Density 0.024%

    No Known Activations