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

    Neuronpedia

    INDEX
    Explanations

    references to JSON and file operations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code block endings or closures

    np_acts-logits-general · gemini-2.0-flash

    ending or concluding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.90
    XmlAccessType
    -0.81
     ExecuteAsync
    -0.81
    __(/*!
    -0.81
     AssemblyTitle
    -0.64
    таратура
    -0.60
     AssemblyProduct
    -0.60
    ValueGeneration
    -0.60
    üyada
    -0.60
    endphp
    -0.59
    POSITIVE LOGITS
     ends
    0.73
     concludes
    0.72
     closing
    0.71
     concluye
    0.68
     end
    0.67
     closes
    0.65
     finished
    0.65
     finish
    0.64
     conclude
    0.64
     conclusion
    0.63
    Act Density 0.259%

    No Known Activations