© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 6251
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `for` loop or `in` keyword (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
     else
    -0.09
    jk
    -0.09
    ili
    -0.09
     while
    -0.09
     continue
    -0.08
    if
    -0.08
    jac
    -0.08
    ility
    -0.08
     if
    -0.08
    ket
    -0.08
    POSITIVE LOGITS
    udok
    0.09
    uzzle
    0.08
    _valid
    0.08
    mpty
    0.07
    uzz
    0.07
     solve
    0.06
    (m
    0.06
    _map
    0.06
    (path
    0.05
    _r
    0.05
    Activations Density 99.732%

    No Known Activations