© 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. 869
    Prev
    Next
    INDEX
    Explanations

    numeric literal 0 (negative activations)

    python-code · gemini-2.5-flash-lite

    calling print or os.system

    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
     '#
    -0.14
     on
    -0.07
     he
    -0.05
    },
    -0.05
     at
    -0.04
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    POSITIVE LOGITS
    rint
    0.41
     print
    0.34
     sys
    0.31
    ilename
    0.25
    splay
    0.23
    _input
    0.20
     usage
    0.20
    print
    0.16
     main
    0.16
     raise
    0.15
    Activations Density 100.000%

    No Known Activations