© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. Residual Stream
    9. 7-RESID
    11. 874
    Prev
    Next
    INDEX
    Explanations

    setter decorator attribute (negative activations)

    python-code · gemini-2.5-flash-lite

    class definition arguments

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cep
    -0.23
    None
    -0.19
    ck
    -0.14
    ique
    -0.11
    é
    -0.09
     th
    -0.08
     b
    -0.07
    _n
    -0.05
     add
    -0.03
    h
    -0.02
    POSITIVE LOGITS
    ted
    0.23
    ound
    0.23
    ard
    0.22
    dition
    0.21
    red
    0.19
    ble
    0.19
    sed
    0.17
    id
    0.17
    ed
    0.17
    uzz
    0.16
    Activations Density 99.961%

    No Known Activations