© 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. 6676
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    string variable assignment (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
    ab
    -0.01
    ord
    -0.01
    q
    -0.01
    _str
    -0.01
    _map
    -0.01
     char
    -0.01
    gs
    -0.00
    The
    -0.00
    .t
    -0.00
    for
    -0.00
    POSITIVE LOGITS
     best
    0.04
    .random
    0.03
     random
    0.03
    random
    0.03
     ""
    0.03
     '
    0.03
     "
    0.03
    ateg
    0.02
     sele
    0.02
     '#
    0.02
    Activations Density 14.167%

    No Known Activations