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

    Neuronpedia

    INDEX
    Explanations

    actors or actresses

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aband
    0.74
    듭
    0.62
    曲線
    0.61
     فرمان
    0.60
    वी
    0.60
     प्रमोद
    0.59
     numbered
    0.57
    \;
    0.57
    機能を
    0.57
     banded
    0.56
    POSITIVE LOGITS
     actors
    3.39
     actor
    3.25
     Actors
    3.07
     Actor
    3.02
    Actor
    2.97
    actor
    2.96
    Actors
    2.95
    actors
    2.93
     actores
    2.89
     actress
    2.87
    Act Density 0.140%

    No Known Activations