© 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. 2-MLP
    11. 3851
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    instance variable suffix

    python-code · gemini-2.5-flash-lite

    .remove( (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
     locations
    -0.08
     low
    -0.08
     best
    -0.08
     obstac
    -0.08
     remaining
    -0.07
     destination
    -0.07
     location
    -0.07
     box
    -0.07
     goal
    -0.06
     room
    -0.06
    POSITIVE LOGITS
    istic
    0.11
    ique
    0.10
    mpty
    0.10
    pected
    0.09
    tive
    0.09
    ual
    0.09
    inary
    0.08
    sible
    0.08
    hest
    0.08
    ·
    0.08
    Activations Density 100.000%

    No Known Activations