© 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. 1933
    Prev
    Next
    INDEX
    Explanations

    printing calculated results (negative activations)

    python-code · gemini-2.5-flash-lite

    attribute names ending in um

    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
    87
    -0.20
    ¬
    -0.19
    ts
    -0.18
    -0.17
    88
    -0.16
    tic
    -0.16
    from
    -0.16
    85
    -0.15
    80
    -0.13
     T
    -0.12
    POSITIVE LOGITS
    ger
    0.27
    0.22
    ames
    0.18
    0.18
    ame
    0.10
    (t
    0.07
    um
    0.07
    '
    0.00
    #
    0.00
    &
    0.00
    Activations Density 99.953%

    No Known Activations