© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 4689
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    class attribute access

    python-code · gemini-2.5-flash-lite

    list index access inside lambda (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
    own
    -0.08
    o
    -0.07
     o
    -0.07
    oc
    -0.06
    ok
    -0.05
     route
    -0.05
    (route
    -0.05
    _city
    -0.05
    route
    -0.05
     routes
    -0.05
    POSITIVE LOGITS
    ateg
    0.15
     best
    0.11
    jective
    0.10
    .random
    0.10
     random
    0.10
    ool
    0.09
    itness
    0.09
    ÷
    0.09
    Á
    0.09
    ø
    0.09
    Activations Density 100.000%

    No Known Activations