© 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. 751
    Prev
    Next
    INDEX
    Explanations

    .format string method (negative activations)

    python-code · gemini-2.5-flash-lite

    `sys.argv` access

    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
    ats
    -0.30
    at
    -0.27
    ater
    -0.20
    att
    -0.19
    ati
    -0.18
    ating
    -0.17
    atch
    -0.17
    ata
    -0.14
    ated
    -0.12
    ator
    -0.10
    POSITIVE LOGITS
    mple
    0.22
    ram
    0.21
    arg
    0.17
    ld
    0.16
     index
    0.13
     i
    0.12
    mp
    0.11
    ser
    0.09
    du
    0.08
    ?
    0.08
    Activations Density 99.984%

    No Known Activations