© 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. MLP
    9. 2-MLP
    11. 7817
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    string literal assignment (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
     __
    -0.10
    __':↵
    -0.10
    __
    -0.09
    __(
    -0.09
    __":↵
    -0.08
     represent
    -0.05
    ]][
    -0.05
    stru
    -0.04
    oc
    -0.03
    .read
    -0.03
    POSITIVE LOGITS
    dint
    0.02
    (),
    0.02
     **
    0.02
    .f
    0.02
     pi
    0.02
    ).
    0.02
    .get
    0.01
    }:
    0.01
    strip
    0.01
    _with
    0.01
    Activations Density 87.857%

    No Known Activations