© 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. 2952
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    method parameter 'g' (negative activations)

    python-code · gemini-2.5-flash-lite

    self.w attributes

    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
    ain
    -0.03
     found
    -0.02
    of
    -0.02
    v
    -0.02
    32
    -0.02
    cur
    -0.02
    Ħ
    -0.02
    line
    -0.01
    lines
    -0.01
    di
    -0.01
    POSITIVE LOGITS
    all
    0.08
     all
    0.07
    uristic
    0.05
    60
    0.05
     any
    0.04
    46
    0.03
    al
    0.03
    ly
    0.03
    us
    0.03
    ique
    0.03
    Activations Density 88.821%

    No Known Activations