© 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. 3449
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    syntax of a tuple or list (negative activations)

    python-code · gemini-2.5-flash-lite

    variable_name.append

    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
    ffe
    -0.03
    [:
    -0.02
    update
    -0.02
    ati
    -0.02
     &
    -0.02
    add
    -0.02
    (a
    -0.02
    c
    -0.01
    ]
    -0.01
     >=
    -0.01
    POSITIVE LOGITS
    [-
    0.07
    ].
    0.07
    ise
    0.03
     [-
    0.03
    .pop
    0.02
     other
    0.02
     True
    0.02
     the
    0.01
     are
    0.01
    sp
    0.01
    Activations Density 98.071%

    No Known Activations