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

    Neuronpedia

    INDEX
    Explanations

    Learn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     valley
    -0.09
    python
    -0.08
    Leak
    -0.08
     leak
    -0.08
    Coordinates
    -0.08
     verlet
    -0.08
     coordinates
    -0.08
     coordinate
    -0.07
    �
    -0.07
     breached
    -0.07
    POSITIVE LOGITS
     Soci
    0.09
     Innovation
    0.09
    дат
    0.09
     parlament
    0.09
     Facts
    0.08
     soci
    0.08
     cartridge
    0.08
    innovation
    0.08
     제목
    0.08
     intitul
    0.08
    Act Density 0.002%

    No Known Activations