© 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. 2-MLP
    11. 5016
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    list index with integer calculation

    python-code · gemini-2.5-flash-lite

    list index access and assignment (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
    ory
    -0.09
    ren
    -0.06
    ump
    -0.06
    resh
    -0.06
    _coordinates
    -0.05
    rap
    -0.05
    ment
    -0.05
    ments
    -0.05
    ķ
    -0.04
    ile
    -0.04
    POSITIVE LOGITS
    ique
    0.08
    pected
    0.08
    tive
    0.07
    mpty
    0.07
     Calculate
    0.07
    ual
    0.07
     **
    0.06
    ·
    0.06
    ary
    0.06
    110
    0.06
    Activations Density 100.000%

    No Known Activations