© 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. 6-MLP
    11. 3335
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    is None check

    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
     Returns
    -0.08
     Output
    -0.05
    isi
    -0.04
     Return
    -0.04
     set
    -0.03
    liver
    -0.03
    E
    -0.03
    O
    -0.03
    V
    -0.03
    F
    -0.03
    POSITIVE LOGITS
    dint
    0.06
    '.
    0.04
    di
    0.04
    inal
    0.04
    {
    0.03
     the
    0.03
    raw
    0.02
    stance
    0.02
    0.01
     contain
    0.01
    Activations Density 5.726%

    No Known Activations