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

    Neuronpedia

    INDEX
    Explanations

    actors and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tabelle
    0.42
     détecter
    0.41
     درصد
    0.39
     ReLU
    0.39
     Sentence
    0.38
     treinta
    0.38
     contenant
    0.38
     geändert
    0.38
     품질
    0.37
     ändern
    0.37
    POSITIVE LOGITS
     roles
    1.23
    角色
    1.10
    出演
    1.04
     appearances
    1.03
    roles
    1.03
     starring
    1.00
     peran
    0.99
    Roles
    0.98
    的角色
    0.98
     portraying
    0.98
    Act Density 0.025%

    No Known Activations