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

    Neuronpedia

    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. 5285
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    float literal after dot

    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
    ble
    -0.06
    for
    -0.06
    sed
    -0.06
    mport
    -0.06
    ted
    -0.05
    ded
    -0.05
    fi
    -0.05
    g
    -0.05
    st
    -0.05
    _
    -0.05
    POSITIVE LOGITS
    is
    0.02
    <extra_output_id:2047>
    0.01
    act
    0.01
     valid
    0.01
     L
    0.01
    ault
    0.01
    ax
    0.01
     best
    0.01
    ction
    0.01
    â
    0.01
    Activations Density 35.951%

    No Known Activations