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

    Neuronpedia

    INDEX
    Explanations

    learning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pcl
    -0.07
     faction
    -0.07
     SEC
    -0.06
    _bit
    -0.06
     Diagram
    -0.06
     پیشنه
    -0.06
    350
    -0.06
    131
    -0.06
     Enemy
    -0.06
     shields
    -0.06
    POSITIVE LOGITS
     Learning
    0.12
    Learning
    0.10
     learning
    0.10
     learners
    0.09
     learner
    0.09
    learning
    0.08
    -task
    0.07
    兒
    0.07
    _movement
    0.07
    Fall
    0.07
    Act Density 0.019%

    No Known Activations