© 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. 7586
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    list assignment or literal (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
    work
    -0.13
    à
    -0.11
     pi
    -0.11
    current
    -0.11
     Node
    -0.11
    ork
    -0.11
    (current
    -0.11
    Æ
    -0.11
    tier
    -0.10
    ats
    -0.10
    POSITIVE LOGITS
    â
    0.17
     continue
    0.13
    jk
    0.13
     open
    0.13
    [n
    0.12
    (n
    0.11
    }"
    0.11
     robot
    0.10
    Â
    0.09
    =None
    0.09
    Activations Density 87.957%

    No Known Activations