© 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. 1225
    Prev
    Next
    INDEX
    Explanations

    numbers with commas or trailing zeros (negative activations)

    python-code · gemini-2.5-flash-lite

    multiplication operator usage

    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
    ens
    -0.23
    ĭ
    -0.20
    bs
    -0.18
    fs
    -0.18
     &
    -0.13
    vers
    -0.13
    ust
    -0.13
    ¾
    -0.12
     ""
    -0.12
    ĥ
    -0.12
    POSITIVE LOGITS
    @
    0.31
    _times
    0.17
     **
    0.15
     Define
    0.12
     >=
    0.12
    app
    0.11
    che
    0.09
    _s
    0.06
     <
    0.06
     <=
    0.05
    Activations Density 97.356%

    No Known Activations