© 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. MLP
    9. 2-MLP
    11. 5197
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    list/dictionary key access

    python-code · gemini-2.5-flash-lite

    dictionary key colon (negative activations)

    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
    _route
    -0.06
    _routes
    -0.06
    cond
    -0.05
     ny
    -0.04
     route
    -0.04
    _location
    -0.04
    location
    -0.04
    (route
    -0.04
    _city
    -0.04
    dividual
    -0.04
    POSITIVE LOGITS
    ÷
    0.12
    Á
    0.12
    ø
    0.12
    þ
    0.12
    À
    0.12
    û
    0.12
    õ
    0.12
    ý
    0.12
    ú
    0.12
    ÿ
    0.12
    Activations Density 100.000%

    No Known Activations