© 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. 4678
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    opening parenthesis in range 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
    ork
    -0.17
    cur
    -0.16
     enum
    -0.15
    ren
    -0.13
    _start
    -0.13
    ateg
    -0.13
    ¢
    -0.13
    ens
    -0.12
    rip
    -0.12
     cur
    -0.12
    POSITIVE LOGITS
    atch
    0.14
    ax
    0.10
     Ex
    0.09
    ue
    0.09
    [row
    0.08
    _max
    0.08
    (max
    0.08
    max
    0.08
     max
    0.07
    [s
    0.07
    Activations Density 98.308%

    No Known Activations