© 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. 1835
    Prev
    Next
    INDEX
    Explanations

    major attribute access (negative activations)

    python-code · gemini-2.5-flash-lite

    attribute access with dot

    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
    _for
    -0.18
    olver
    -0.15
    hip
    -0.14
     form
    -0.12
    50
    -0.08
    200
    -0.08
    100
    -0.06
    150
    -0.04
    '
    0.00
    #
    0.00
    POSITIVE LOGITS
    ger
    0.22
    port
    0.20
    ol
    0.18
    ordinate
    0.16
    ner
    0.15
    irst
    0.14
     parent
    0.14
    arent
    0.14
    ost
    0.12
    layer
    0.12
    Activations Density 100.000%

    No Known Activations