© 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. 5676
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    list elements and commas

    python-code · gemini-2.5-flash-lite

    end of nested list `]]` (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
     best
    -0.10
    erson
    -0.05
    _coordinates
    -0.05
    apac
    -0.05
     optim
    -0.04
     sele
    -0.04
    ordinate
    -0.04
    bab
    -0.04
    _cost
    -0.04
    ateg
    -0.04
    POSITIVE LOGITS
    ð
    0.09
     ny
    0.06
     nx
    0.04
    ad
    0.04
     Calculate
    0.04
    .randint
    0.04
    def
    0.04
     sys
    0.04
    etween
    0.03
    ]]↵
    0.03
    Activations Density 100.000%

    No Known Activations