© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 4758
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    attribute or method names ending in _n or _by

    python-code · gemini-2.5-flash-lite

    declaration of class or function (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
    essage
    -0.06
    dividual
    -0.06
    arent
    -0.04
    isited
    -0.04
    visited
    -0.04
    [-
    -0.03
    ackage
    -0.03
    rt
    -0.02
    ă
    -0.02
    ct
    -0.02
    POSITIVE LOGITS
    inal
    0.09
    (new
    0.07
    cores
    0.07
    instance
    0.07
    vai
    0.06
    reate
    0.06
    over
    0.06
    raph
    0.06
    riority
    0.05
    etwork
    0.05
    Activations Density 100.000%

    No Known Activations