© 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. 6-MLP
    11. 5510
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    json.dumps indent argument

    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
     key
    -0.07
    (key
    -0.07
    alculate
    -0.07
    keys
    -0.07
    _key
    -0.06
    key
    -0.06
    is
    -0.05
    verse
    -0.05
     default
    -0.05
     calculate
    -0.04
    POSITIVE LOGITS
    pe
    0.15
     p
    0.11
     dist
    0.10
     distances
    0.10
    _p
    0.09
     distance
    0.08
    (p
    0.07
    ĥ
    0.07
     range
    0.07
    [p
    0.07
    Activations Density 16.789%

    No Known Activations