© 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

    attribute access `self.name` (negative activations)

    python-code · gemini-2.5-flash-lite

    exponentiation of 2

    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
    [(
    -0.05
    ((
    -0.04
    (str
    -0.03
    set
    -0.03
    ['
    -0.03
    (min
    -0.02
    (max
    -0.02
    (maze
    -0.02
    [-
    -0.02
    (self
    -0.02
    Positive Logits
    raw
    0.01
    0.01
    fs
    0.01
     ro
    0.01
    ffe
    0.01
    j
    0.01
     in
    0.00
     int
    0.00
     sum
    0.00
    ac
    0.00
    Activations Density 96.952%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    return statement or attribute access (negative activations)

    python-code · gemini-2.5-flash-lite

    attribute access `.right`

    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
    ec
    -0.02
    _start
    -0.01
     start
    -0.01
    _left
    -0.01
     left
    -0.01
     source
    -0.01
    .values
    -0.01
    start
    -0.01
     or
    -0.01
    .start
    -0.01
    Positive Logits
    join
    0.08
    oal
    0.06
    stination
    0.06
    arget
    0.05
     right
    0.05
     second
    0.05
    other
    0.04
     goal
    0.04
    right
    0.04
     destination
    0.04
    Activations Density 99.541%

    No Known Activations