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

    Neuronpedia

    INDEX
    Explanations

    Code/programming

    np_max-act · gemini-2.0-flash

    The neuron fires on programming‐language syntax (code fences and keywords like `fn`, `println`, `import`, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .cornerRadius
    -0.07
    .isChecked
    -0.06
    Patrick
    -0.06
     Imports
    -0.06
     stripe
    -0.06
    azing
    -0.06
    sunuz
    -0.06
     Surgical
    -0.06
    Atual
    -0.06
     mac
    -0.06
    POSITIVE LOGITS
     فیلم
    0.07
     ном
    0.06
     品
    0.06
     로
    0.06
    Learn
    0.06
     термін
    0.06
     Insights
    0.06
     contacting
    0.06
    λεκ
    0.06
    yh
    0.06
    Act Density 0.144%

    No Known Activations