© 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. 4893
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    function or import statement (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
     Returns
    -0.08
    el
    -0.06
    s
    -0.06
     Output
    -0.05
     Return
    -0.05
     of
    -0.05
    lable
    -0.04
    of
    -0.04
    (self
    -0.04
    _of
    -0.04
    POSITIVE LOGITS
    _city
    0.15
    ities
    0.09
    city
    0.09
     city
    0.09
    _cities
    0.09
    ity
    0.09
     cities
    0.09
    gion
    0.08
    .heapp
    0.08
    .parent
    0.07
    Activations Density 99.529%

    No Known Activations