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

    Neuronpedia

    INDEX
    Explanations

    sharks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    িন
    0.81
    fileExistsAtPath
    0.81
     Мето
    0.79
     Сурикова
    0.79
    가가
    0.78
     Цуки
    0.78
    ۔
    0.78
    берриз
    0.77
    녈
    0.75
     Суриков
    0.75
    POSITIVE LOGITS
    -
    1.03
    '
    1.02
     shark
    1.01
    ’
    1.01
     sharks
    1.00
    et
    0.97
    t
    0.97
     at
    0.94
    shark
    0.93
     Shark
    0.86
    Act Density 0.002%

    No Known Activations