© 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. 1788
    Prev
    Next
    INDEX
    Explanations

    dot prefix for attribute access (negative activations)

    python-code · gemini-2.5-flash-lite

    attribute access and assignments

    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
    jk
    -0.21
    lt
    -0.20
    44
    -0.15
    sign
    -0.14
    į
    -0.13
    gram
    -0.13
    40
    -0.12
    43
    -0.12
    45
    -0.12
    ample
    -0.11
    POSITIVE LOGITS
    urn
    0.23
    Ŀ
    0.18
    ove
    0.17
     \
    0.15
    101
    0.11
    _block
    0.10
    lock
    0.06
    85
    0.06
    ach
    0.05
    '
    0.00
    Activations Density 100.000%

    No Known Activations