© 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. 711
    Prev
    Next
    INDEX
    Explanations

    self.p·h·one attribute access (negative activations)

    python-code · gemini-2.5-flash-lite

    turtle

    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
    split
    -0.20
     plt
    -0.19
    isit
    -0.17
    _neighbor
    -0.16
     neighbor
    -0.16
    lot
    -0.15
    _sp
    -0.15
    neighbor
    -0.15
    17
    -0.13
    one
    -0.12
    POSITIVE LOGITS
    ye
    0.21
    je
    0.21
    pe
    0.17
    _me
    0.15
    _le
    0.15
    me
    0.14
    32
    0.14
     spe
    0.14
     we
    0.13
    _ele
    0.13
    Activations Density 97.563%

    No Known Activations