© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. Residual Stream
    9. 7-RESID
    11. 1221
    Prev
    Next
    INDEX
    Explanations

    for loop with variable assignment (negative activations)

    python-code · gemini-2.5-flash-lite

    key in sorted() with lambda

    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
    fset
    -0.26
     possible
    -0.21
    hor
    -0.21
     directions
    -0.20
     neighbors
    -0.18
     adjac
    -0.15
     moves
    -0.14
     dx
    -0.13
     adj
    -0.13
     direction
    -0.13
    POSITIVE LOGITS
     form
    0.21
     If
    0.10
     optim
    0.08
     results
    0.06
    _m
    0.03
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    Activations Density 100.000%

    No Known Activations