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

    Neuronpedia

    INDEX
    Explanations

    constraints between objects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     badly
    -0.08
     benefiting
    -0.08
     Tips
    -0.08
    Tips
    -0.08
    _TOPIC
    -0.08
    ionar
    -0.08
     Topics
    -0.08
    .Topic
    -0.08
     radios
    -0.08
     brasileira
    -0.08
    POSITIVE LOGITS
     расстоя
    0.09
    Shortest
    0.09
     spacer
    0.08
     funct
    0.08
     shortest
    0.08
    距离
    0.07
    usize
    0.07
     दूरी
    0.07
    -short
    0.07
     очередь
    0.07
    Act Density 0.011%

    No Known Activations