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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     сили
    -0.06
    (A
    -0.06
    plements
    -0.06
     ((!
    -0.06
     deportation
    -0.06
     contiene
    -0.06
    улю
    -0.06
     Созд
    -0.06
     FROM
    -0.06
     geometry
    -0.06
    POSITIVE LOGITS
     बय
    0.07
     Anth
    0.07
     Exam
    0.06
     Sophia
    0.06
    407
    0.06
    components
    0.06
     helped
    0.06
     blessed
    0.06
    (options
    0.06
    task
    0.06
    Act Density 0.059%

    No Known Activations