© 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. 6109
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable name prefix _

    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
    [int
    -0.14
    loat
    -0.12
    (int
    -0.11
    int
    -0.11
     int
    -0.10
     float
    -0.09
    (self
    -0.08
    (list
    -0.06
     self
    -0.06
    (str
    -0.06
    POSITIVE LOGITS
    ke
    0.05
    re
    0.05
    count
    0.05
    sw
    0.05
    index
    0.04
    param
    0.04
    per
    0.04
    city
    0.04
    he
    0.04
    par
    0.04
    Activations Density 43.587%

    No Known Activations