© 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. 4641
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    statistics

    python-code · gemini-2.5-flash-lite

    assignment or comparison operators (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
    graph
    -0.05
    ax
    -0.02
     values
    -0.02
    inf
    -0.02
     code
    -0.02
     can
    -0.02
     has
    -0.02
    ac
    -0.02
    row
    -0.02
    ak
    -0.02
    POSITIVE LOGITS
    xF
    0.10
    ger
    0.08
    ket
    0.08
    ory
    0.06
    gest
    0.06
    loat
    0.05
    ward
    0.05
    rences
    0.05
    ili
    0.04
    rence
    0.04
    Activations Density 100.000%

    No Known Activations