© 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
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. Residual Stream
    9. 7-RESID
    11. 1609
    Prev
    Next
    INDEX
    Explanations

    for loop iteration variables (negative activations)

    python-code · gemini-2.5-flash-lite

    for loop keywords

    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
    mmand
    -0.26
    quest
    -0.22
    text
    -0.20
     command
    -0.18
    anage
    -0.17
    _data
    -0.16
    ustom
    -0.14
    user
    -0.14
     test
    -0.14
     data
    -0.13
    POSITIVE LOGITS
    ast
    0.10
     o
    0.08
     abs
    0.07
     al
    0.06
    ak
    0.05
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    Activations Density 100.000%

    No Known Activations