© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    Side-by-side compare needs a wider screen.
    Open other featureClose compare
    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    is or is not

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    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
    Negative Logits
    instance
    -0.09
    att
    -0.05
       
    -0.04
    @
    -0.04
    2
    -0.04
    .add
    -0.03
     and
    -0.03
    ă
    -0.03
    _to
    -0.03
    ė
    -0.03
    Positive Logits
     {
    0.03
    xF
    0.02
    ing
    0.02
    dition
    0.02
     found
    0.02
     _
    0.02
     if
    0.02
    ((
    0.02
     nodes
    0.01
    ...
    0.01
    Activations Density 30.622%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment statement

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    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
    Negative Logits
    ith
    -0.05
    quired
    -0.05
    ne
    -0.05
     with
    -0.04
    wo
    -0.04
    mp
    -0.03
    _path
    -0.03
     path
    -0.03
     ne
    -0.03
    _ne
    -0.03
    Positive Logits
     pi
    0.07
     ny
    0.06
    y
    0.06
     dy
    0.06
    Y
    0.05
     Y
    0.05
    it
    0.05
    for
    0.05
    .y
    0.05
    _y
    0.05
    Activations Density 68.442%

    No Known Activations