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

    Neuronpedia

    INDEX
    Explanations

    Abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .delivery
    -0.07
    /User
    -0.07
     pigs
    -0.06
     행
    -0.06
    employee
    -0.06
    وز
    -0.06
    ंज
    -0.06
    ialog
    -0.06
    ../
    -0.06
    .Constraint
    -0.06
    POSITIVE LOGITS
     engage
    0.06
     söylem
    0.06
    -centered
    0.06
    splice
    0.06
     виник
    0.06
    Phoenix
    0.06
     цей
    0.06
     eder
    0.05
     віт
    0.05
     Suppress
    0.05
    Act Density 0.085%

    No Known Activations