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

    Neuronpedia

    INDEX
    Explanations

    princess plus name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Deputy
    0.48
    శ
    0.44
     डिप्टी
    0.43
     deputy
    0.43
    쁩
    0.41
    太太
    0.41
    taining
    0.39
     bà
    0.39
     उपयुक्त
    0.38
     son
    0.38
    POSITIVE LOGITS
     Leia
    0.49
    Leia
    0.47
    🏰
    0.46
     Palace
    0.42
    engagement
    0.42
     হারানোর
    0.42
    ensa
    0.41
     dresses
    0.41
    ❈
    0.41
     castles
    0.40
    Act Density 0.004%

    No Known Activations