© 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. 1810
    Prev
    Next
    INDEX
    Explanations

    dict.fromkeys (negative activations)

    python-code · gemini-2.5-flash-lite

    assigning to variable

    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
    <extra_output_id:2047>
    -0.19
    &
    0.00
    #
    0.00
    '
    0.00
    *
    0.00
    %
    0.00
    )
    0.00
    !
    0.00
    "
    0.00
    $
    0.00
    POSITIVE LOGITS
    _cities
    0.43
    _room
    0.30
    _routes
    0.29
    __(
    0.26
    _cell
    0.22
    _vertex
    0.21
    (maze
    0.21
    _paths
    0.18
    _location
    0.17
    .position
    0.17
    Activations Density 99.247%

    No Known Activations