© 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. 6-MLP
    11. 6234
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `str` literal followed by parenthesis (negative activations)

    python-code · gemini-2.5-flash-lite

    string format method call

    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
    mple
    -0.03
    ram
    -0.03
    V
    -0.03
     V
    -0.03
    arg
    -0.03
    ld
    -0.02
     index
    -0.02
     i
    -0.02
    mp
    -0.02
    ser
    -0.01
    POSITIVE LOGITS
    ats
    0.05
    at
    0.04
    .heapp
    0.03
    ater
    0.03
    att
    0.03
    ati
    0.03
    ating
    0.03
    atch
    0.03
    [y
    0.02
    .remove
    0.02
    Activations Density 92.241%

    No Known Activations