© 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. 1983
    Prev
    Next
    INDEX
    Explanations

    .lower() (negative activations)

    python-code · gemini-2.5-flash-lite

    tuple literal or argument

    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
    add
    -0.15
    set
    -0.12
    k
    -0.08
    100
    -0.07
    values
    -0.05
    text
    -0.03
     "
    -0.03
    '
    0.00
    #
    0.00
    &
    0.00
    POSITIVE LOGITS
    from
    0.23
     neighbor
    0.21
     next
    0.18
     adjac
    0.17
    new
    0.17
     ne
    0.16
     adj
    0.15
     dep
    0.14
    neighbor
    0.13
     child
    0.11
    Activations Density 99.949%

    No Known Activations