© 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. 3950
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    method argument (negative activations)

    python-code · gemini-2.5-flash-lite

    method argument or 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
     q
    -0.05
    q
    -0.04
    gs
    -0.03
     r
    -0.02
    .d
    -0.02
    Q
    -0.02
     whi
    -0.02
    :
    -0.02
    (min
    -0.02
    (max
    -0.02
    POSITIVE LOGITS
    ffe
    0.04
    ig
    0.03
    1
    0.03
    imum
    0.03
    ci
    0.02
     [
    0.02
    adjac
    0.02
    No
    0.02
    ner
    0.02
     n
    0.02
    Activations Density 99.175%

    No Known Activations