© 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. 4790
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    multiplication and multiply methods

    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
     obstac
    -0.04
     destination
    -0.04
     box
    -0.04
     goal
    -0.03
     room
    -0.03
     person
    -0.03
     robot
    -0.03
     child
    -0.03
     team
    -0.03
     rule
    -0.03
    POSITIVE LOGITS
    ls
    0.09
    l
    0.07
    men
    0.06
    les
    0.06
    L
    0.05
     lon
    0.05
    re
    0.05
    ld
    0.04
     L
    0.04
    ag
    0.04
    Activations Density 54.721%

    No Known Activations