© 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. 5019
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    special method `__mul__`

    python-code · gemini-2.5-flash-lite

    attribute access (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
    rite
    -0.09
     continue
    -0.08
    inal
    -0.08
    =None
    -0.06
    thod
    -0.06
    inations
    -0.05
    ates
    -0.05
    ination
    -0.05
    -0.04
     None
    -0.04
    POSITIVE LOGITS
    ilities
    0.10
    iz
    0.08
    ise
    0.08
    ens
    0.07
    ized
    0.07
    en
    0.07
    rt
    0.06
    self
    0.06
    sp
    0.06
    ency
    0.05
    Activations Density 100.000%

    No Known Activations