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

    Neuronpedia

    INDEX
    Explanations

    superstar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ইন্দিরা
    0.42
     phụ
    0.41
    Legends
    0.40
     Emergency
    0.39
    杢
    0.39
    Emergency
    0.38
    нович
    0.38
     इंदिरा
    0.38
     Té
    0.37
     emergency
    0.36
    POSITIVE LOGITS
     superstar
    0.67
     superstars
    0.63
     Superstar
    0.63
     MVP
    0.57
     stardom
    0.53
     star
    0.50
     elite
    0.48
     stars
    0.47
    mv
    0.46
     meg
    0.46
    Act Density 0.009%

    No Known Activations