© 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. 6-MLP
    11. 5307
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `abs` or `activation`

    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
    dom
    -0.08
     val
    -0.05
    atus
    -0.05
    ata
    -0.04
     var
    -0.04
     loc
    -0.04
    able
    -0.04
    fo
    -0.04
    mo
    -0.03
    inf
    -0.03
    POSITIVE LOGITS
    ove
    0.07
     dx
    0.06
    prese
    0.05
    °
    0.04
    loat
    0.04
    ¸
    0.04
    ces
    0.04
    ¾
    0.03
    ven
    0.03
    µ
    0.03
    Activations Density 20.086%

    No Known Activations