© 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. 6560
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    month 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
    ate
    -0.02
    ates
    -0.02
    ated
    -0.02
    Į
    -0.02
    :
    -0.02
    Ħ
    -0.02
    ating
    -0.02
     =
    -0.02
    ategory
    -0.02
    ation
    -0.02
    POSITIVE LOGITS
    ize
    0.05
    ilities
    0.04
    iz
    0.04
    ized
    0.04
    ise
    0.03
    ility
    0.02
    al
    0.02
    old
    0.02
    als
    0.02
    all
    0.02
    Activations Density 12.468%

    No Known Activations