© 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. 2-MLP
    11. 7927
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    index access or list slicing (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
    [start
    -0.19
    [current
    -0.18
    á
    -0.15
     current
    -0.15
    (current
    -0.14
    Æ
    -0.14
     end
    -0.13
    _end
    -0.12
    (start
    -0.12
     obstac
    -0.12
    POSITIVE LOGITS
     I
    0.08
    _str
    0.07
    I
    0.07
    .ch
    0.06
    _route
    0.06
    _code
    0.06
    _tree
    0.06
    _solution
    0.05
    _string
    0.05
    _routes
    0.05
    Activations Density 96.789%

    No Known Activations