© 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. 1444
    Prev
    Next
    INDEX
    Explanations

    string literal followed by quote (negative activations)

    python-code · gemini-2.5-flash-lite

    search method calls

    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
     Graph
    -0.14
    _order
    -0.12
    order
    -0.12
                    ↵
    -0.12
    IJ
    -0.12
    Ð
    -0.11
    ch
    -0.11
     order
    -0.11
    22
    -0.10
     moves
    -0.09
    POSITIVE LOGITS
    arch
    0.23
    ´
    0.19
    ck
    0.18
     Check
    0.16
    ude
    0.16
    _move
    0.16
    heck
    0.16
    ove
    0.16
    roup
    0.15
    í
    0.15
    Activations Density 100.000%

    No Known Activations