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

    Neuronpedia

    INDEX
    Explanations

    Questions and Answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    partition
    -0.07
     identities
    -0.07
    stops
    -0.06
    .calendar
    -0.06
    burger
    -0.06
     occupied
    -0.06
     Values
    -0.06
     道
    -0.06
    .components
    -0.06
     sophisticated
    -0.06
    POSITIVE LOGITS
    Karen
    0.07
     Mexican
    0.07
    @SpringBootApplication
    0.07
    нося
    0.06
    ΡΓ
    0.06
     Karen
    0.06
     треть
    0.06
     Lily
    0.06
    ونی
    0.06
     SEO
    0.06
    Act Density 0.248%

    No Known Activations