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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 3220
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable 'a' assignment or call

    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
    lat
    -0.11
    itude
    -0.10
     lat
    -0.09
    ge
    -0.06
     },↵
    -0.06
    °
    -0.06
    ¸
    -0.04
    Į
    -0.04
    ¾
    -0.03
    ss
    -0.03
    POSITIVE LOGITS
    _an
    0.07
    an
    0.07
    B
    0.07
    ant
    0.06
    le
    0.06
     B
    0.06
    ance
    0.06
    art
    0.06
    les
    0.06
     an
    0.06
    Activations Density 7.224%

    No Known Activations