© 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. 1855
    Prev
    Next
    INDEX
    Explanations

    balance attribute access (negative activations)

    python-code · gemini-2.5-flash-lite

    date of birth

    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
    ance
    -0.29
    ant
    -0.29
    an
    -0.17
    and
    -0.12
    ue
    -0.10
    ues
    -0.10
    un
    -0.09
    nt
    -0.09
    dd
    -0.06
    '
    0.00
    POSITIVE LOGITS
    ®
    0.31
    vailable
    0.15
    for
    0.10
    ath
    0.08
    ch
    0.04
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    Activations Density 99.585%

    No Known Activations