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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Weight-Sparse Transformers
    3. CircuitGPT-Python
    4. Residual Stream
    5. 7-RESID
    6. 1844
    Prev
    Next
    INDEX
    Explanations

    print call with arguments (negative activations)

    python-code · gemini-2.5-flash-lite

    '(' followed by string literal

    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
    ven
    -0.08
    ress
    -0.06
    urn
    -0.05
     on
    -0.04
     items
    -0.04
     ad
    -0.04
     tra
    -0.04
     ac
    -0.04
    K
    -0.03
     o
    -0.03
    POSITIVE LOGITS
     dictionary
    0.22
    ctionary
    0.22
    uple
    0.19
     deque
    0.19
     dict
    0.19
     Tuple
    0.19
     List
    0.18
    _dict
    0.17
     tuple
    0.17
    dict
    0.16
    Activations Density 99.779%

    No Known Activations