© 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. 3798
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment to self.color

    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
    ±
    -0.03
     found
    -0.02
     :
    -0.02
    ?
    -0.02
    07
    -0.02
    ef
    -0.02
     (
    -0.01
    bab
    -0.01
    _grid
    -0.01
    -0.01
    POSITIVE LOGITS
    [v
    0.10
    (v
    0.09
     v
    0.09
    v
    0.07
    _v
    0.06
    m
    0.06
    me
    0.05
    vi
    0.04
    men
    0.04
    vel
    0.04
    Activations Density 32.693%

    No Known Activations