© 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
    2. OpenAI · Weight-Sparse Transformers
    3. CircuitGPT-Python
    4. MLP
    5. 2-MLP
    6. 4897
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    uuid.uuid4() call or dictionary keys

    python-code · gemini-2.5-flash-lite

    list type hint or list constructor (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
    _city
    -0.05
    .parent
    -0.05
    _distances
    -0.05
     defaultdict
    -0.05
    _vertex
    -0.05
    _capacity
    -0.04
    _room
    -0.04
    .index
    -0.04
    90
    -0.04
    60
    -0.04
    POSITIVE LOGITS
    mpty
    0.12
    _total
    0.11
    uzzle
    0.10
    otal
    0.10
    udok
    0.10
    join
    0.09
    raw
    0.09
    uzz
    0.09
    ^
    0.09
    ra
    0.09
    Activations Density 100.000%

    No Known Activations