© 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. 710
    Prev
    Next
    INDEX
    Explanations

    accessing attributes like `release_y` (negative activations)

    python-code · gemini-2.5-flash-lite

    parts of words in attribute access

    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
    ger
    -0.11
     position
    -0.11
    _position
    -0.06
    26
    -0.05
    85
    -0.04
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    POSITIVE LOGITS
    ª
    0.24
    ases
    0.22
    ase
    0.21
    gn
    0.20
     pos
    0.18
    200
    0.16
    as
    0.15
    19
    0.14
    21
    0.14
    20
    0.13
    Activations Density 99.747%

    No Known Activations