© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 5456
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    list or tuple element access (negative activations)

    python-code · gemini-2.5-flash-lite

    `dict` key access

    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
    join
    -0.04
    lable
    -0.03
     not
    -0.03
    mport
    -0.02
    |>
    -0.02
    ator
    -0.01
    ser
    -0.01
    un
    -0.01
    lit
    -0.01
    :↵
    -0.01
    POSITIVE LOGITS
    =
    0.03
    quired
    0.03
     -=
    0.03
    ho
    0.02
    ob
    0.01
    mpty
    0.01
     given
    0.01
     or
    0.01
    ave
    0.01
    Error
    0.01
    Activations Density 99.932%

    No Known Activations