© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 3228
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    elif statement condition (negative activations)

    python-code · gemini-2.5-flash-lite

    method call `()` after `magnitude`

    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
    name
    -0.03
     second
    -0.03
     name
    -0.03
    or
    -0.03
    ilename
    -0.03
    .name
    -0.03
    _name
    -0.02
    .id
    -0.02
    _set
    -0.02
     id
    -0.02
    POSITIVE LOGITS
    umn
    0.03
    (row
    0.02
     g
    0.02
     e
    0.02
     b
    0.02
     d
    0.02
     p
    0.02
     s
    0.02
     f
    0.01
     m
    0.01
    Activations Density 7.352%

    No Known Activations