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

    Neuronpedia

    INDEX
    Explanations

    movie actors and actresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SaaS
    0.66
     IoT
    0.63
     Oculus
    0.61
     Fitbit
    0.59
     LiDAR
    0.59
     ReLU
    0.56
     OnePlus
    0.55
     Macbook
    0.55
     VMware
    0.55
     iOS
    0.54
    POSITIVE LOGITS
    演員
    0.64
    電影
    0.63
     배우
    0.59
     starring
    0.58
     actresses
    0.57
     films
    0.55
     stardom
    0.55
     actress
    0.54
    女優
    0.54
     Bronson
    0.53
    Act Density 0.016%

    No Known Activations