© 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. 6148
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    end of tuple or method call argument

    python-code · gemini-2.5-flash-lite

    list of numbers with commas (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
    uel
    -0.04
    #
    -0.04
     #
    -0.04
    ))
    -0.03
     top
    -0.03
    ode
    -0.03
     char
    -0.03
    otal
    -0.03
    A
    -0.03
     adj
    -0.03
    POSITIVE LOGITS
    mpty
    0.06
     "__
    0.06
     '__
    0.06
     Value
    0.05
    _valid
    0.05
    .current
    0.05
    istic
    0.05
    ded
    0.05
    ure
    0.05
    ary
    0.04
    Activations Density 100.000%

    No Known Activations