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

    Neuronpedia

    INDEX
    Explanations

    commands

    np_max-act · gemini-2.0-flash

    This neuron identifies mentions of internal command names or invocation tokens (e.g. “analyze_code,” “execute_python_file,” “append_to_file,” “google,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     $('
    -0.07
    Pok
    -0.07
     takeaway
    -0.07
    Way
    -0.07
    ลา
    -0.06
     $("
    -0.06
     minib
    -0.06
     quý
    -0.06
    카
    -0.06
     世
    -0.06
    POSITIVE LOGITS
     asthma
    0.07
    ertificate
    0.07
     Crimson
    0.07
     뒤
    0.06
    plementation
    0.06
    測
    0.06
    ression
    0.06
    EventArgs
    0.06
     Eastern
    0.06
    <![
    0.06
    Act Density 0.010%

    No Known Activations