© 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. 3751
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    return value of a function (negative activations)

    python-code · gemini-2.5-flash-lite

    email or year attribute

    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
    ost
    -0.03
    reshold
    -0.02
     continue
    -0.02
     open
    -0.01
     iter
    -0.01
    ateg
    -0.01
     assign
    -0.01
     process
    -0.01
     steps
    -0.01
    :
    -0.01
    POSITIVE LOGITS
    <extra_output_id:2047>
    0.03
    [(
    0.02
    [j
    0.02
     ↵
    0.02
    ]],
    0.02
    )):↵
    0.01
    ]]
    0.01
    ]]↵
    0.01
    st
    0.01
    )]↵↵
    0.01
    Activations Density 99.996%

    No Known Activations