© 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. 6-MLP
    11. 4977
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    addition operator (negative activations)

    python-code · gemini-2.5-flash-lite

    append to list

    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
     dist
    -0.02
     steps
    -0.02
    .parent
    -0.02
    co
    -0.02
    ri
    -0.02
    uel
    -0.01
     !=
    -0.01
     is
    -0.01
    _cost
    -0.01
    value
    -0.01
    POSITIVE LOGITS
    ][
    0.02
    .append
    0.02
    [(
    0.02
    ((
    0.01
    .pop
    0.01
    en
    0.01
    _edge
    0.01
     sele
    0.01
     else
    0.01
     min
    0.01
    Activations Density 69.194%

    No Known Activations