© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1608
    Prev
    Next
    INDEX
    Explanations

    most_common method call (negative activations)

    python-code · gemini-2.5-flash-lite

    0 followed by a dot

    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
    isited
    -0.39
    orted
    -0.21
    maining
    -0.21
    visited
    -0.20
    quired
    -0.20
    use
    -0.19
    ted
    -0.17
    red
    -0.17
    ded
    -0.15
    ef
    -0.14
    POSITIVE LOGITS
    15
    0.11
    form
    0.10
    Ń
    0.09
    01
    0.09
    ord
    0.09
    's
    0.08
    25
    0.07
    k
    0.06
    im
    0.05
     G
    0.05
    Activations Density 99.991%

    No Known Activations