© 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. 1432
    Prev
    Next
    INDEX
    Explanations

    activation='str' (negative activations)

    python-code · gemini-2.5-flash-lite

    decimal, factorial, animal

    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
    Ħ
    -0.22
    line
    -0.19
    lines
    -0.17
    Ī
    -0.14
    ctor
    -0.08
    loc
    -0.07
    age
    -0.06
    ge
    -0.05
    '
    0.00
    #
    0.00
    POSITIVE LOGITS
    al
    0.25
    old
    0.24
    als
    0.23
    all
    0.23
    ject
    0.14
    ual
    0.14
    ore
    0.11
     th
    0.05
    '
    0.00
    #
    0.00
    Activations Density 98.549%

    No Known Activations