Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Database design

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     toothpaste
    -0.09
    _agent
    -0.09
    Agent
    -0.08
     coward
    -0.08
    (agent
    -0.08
     agent
    -0.08
    -agent
    -0.08
     восп
    -0.08
    Playback
    -0.08
     ingesteld
    -0.08
    POSITIVE LOGITS
    (schema
    0.15
    /schema
    0.14
     schema
    0.14
    .Schema
    0.14
     schemas
    0.14
    .schema
    0.13
     diagrams
    0.13
     UML
    0.13
     diagram
    0.13
    \Schema
    0.13
    Act Density 0.023%

    No Known Activations