© 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. 7782
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    .remove method call

    python-code · gemini-2.5-flash-lite

    imaginary part of complex numbers (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
    alue
    -0.10
    mmon
    -0.10
    Ë
    -0.10
    alculate
    -0.10
    pected
    -0.10
    losest
    -0.09
    mmand
    -0.09
    distan
    -0.08
    apac
    -0.08
    straints
    -0.08
    POSITIVE LOGITS
     Testing
    0.06
    ho
    0.06
    od
    0.05
    oc
    0.05
    o
    0.05
    over
    0.05
    own
    0.05
    test
    0.05
     o
    0.05
    instance
    0.05
    Activations Density 100.000%

    No Known Activations