© 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. 4664
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    if followed by condition (negative activations)

    python-code · gemini-2.5-flash-lite

    `for` loop unpacks, assignment, list/tuple constructor

    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
     and
    -0.05
     &
    -0.04
     y
    -0.04
     j
    -0.03
    ]):↵
    -0.03
     ↵
    -0.03
     float
    -0.03
     ob
    -0.02
    ):↵
    -0.02
     i
    -0.02
    POSITIVE LOGITS
    ss
    0.05
    0.05
    0.04
    um
    0.03
    ct
    0.03
    ap
    0.03
    '.
    0.02
    ls
    0.02
    te
    0.02
    Ģ
    0.02
    Activations Density 50.928%

    No Known Activations