© 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. 8130
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable name 'j' (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
    _city
    -0.06
    city
    -0.06
     dx
    -0.06
     city
    -0.06
    xF
    -0.06
    _cities
    -0.05
    xb
    -0.05
    _x
    -0.05
     cities
    -0.05
    xc
    -0.05
    POSITIVE LOGITS
     heuristic
    0.13
    uristic
    0.13
     score
    0.11
    _scores
    0.10
    rontier
    0.10
    cores
    0.09
    _score
    0.09
    oal
    0.09
     goal
    0.09
    core
    0.08
    Activations Density 96.230%

    No Known Activations