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

    Neuronpedia

    INDEX
    Explanations

    practices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     practices
    -1.73
     experiences
    -1.50
     processes
    -1.40
    practices
    -1.27
     Practices
    -1.21
    experiences
    -1.12
    processes
    -1.10
     PRACTICES
    -1.09
     uses
    -1.09
     Experiences
    -1.01
    POSITIVE LOGITS
     comando
    0.66
    Tikang
    0.55
    Ingrédients
    0.54
    heets
    0.53
     متعلقه
    0.52
     विश्वसनीयता
    0.51
     بيها
    0.51
    makeConstraints
    0.50
    ècie
    0.50
    Funds
    0.50
    Act Density 0.110%

    No Known Activations