© 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. 2-MLP
    11. 4013
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable assignment with str (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
    |>
    -0.11
    lit
    -0.09
    ut
    -0.05
    '.
    -0.04
    of
    -0.03
    ram
    -0.02
    ases
    -0.02
    tic
    -0.01
    ates
    -0.01
    ays
    -0.01
    POSITIVE LOGITS
     or
    0.06
    s
    0.04
    (self
    0.02
    ns
    0.02
    section
    0.02
     self
    0.02
    self
    0.02
    ure
    0.02
    ctor
    0.01
    ment
    0.01
    Activations Density 44.599%

    No Known Activations