© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 7569
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `connect` or `output` keywords

    python-code · gemini-2.5-flash-lite

    'if' statement condition (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
     student
    -0.07
     team
    -0.07
     destination
    -0.07
     tasks
    -0.07
    _tasks
    -0.07
     room
    -0.07
     person
    -0.06
     task
    -0.06
     routes
    -0.06
     child
    -0.06
    POSITIVE LOGITS
    rue
    0.11
    .read
    0.08
    ]][
    0.07
    0.06
    dition
    0.06
    0.05
    0.05
    alc
    0.04
                ↵
    0.04
    gram
    0.04
    Activations Density 100.000%

    No Known Activations