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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 4964
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment to variable 'a'

    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
    I
    -0.08
     model
    -0.07
    odel
    -0.06
    .add
    -0.05
    .remove
    -0.05
    stance
    -0.05
    ul
    -0.04
    straint
    -0.04
    straints
    -0.04
     ob
    -0.03
    POSITIVE LOGITS
    mport
    0.07
    .is
    0.05
     the
    0.04
    duct
    0.04
     The
    0.04
    hild
    0.03
    _neighbor
    0.03
    .name
    0.03
    The
    0.03
     new
    0.03
    Activations Density 87.005%

    No Known Activations