© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. Residual Stream
    9. 7-RESID
    11. 165
    Prev
    Next
    INDEX
    Explanations

    statistics module functions

    python-code · gemini-2.5-flash-lite

    accessing attributes with dot notation (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
    ness
    -0.26
    ul
    -0.18
     ['
    -0.16
    ra
    -0.16
    Ñ
    -0.13
    İ
    -0.13
    _route
    -0.12
    ck
    -0.11
    !
    -0.11
    qu
    -0.10
    POSITIVE LOGITS
    ic
    0.23
    ri
    0.19
    Ĭ
    0.18
    $
    0.15
    riend
    0.14
    _se
    0.14
    qui
    0.14
    ari
    0.13
    vi
    0.13
    li
    0.12
    Activations Density 100.000%

    No Known Activations