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

    Neuronpedia

    INDEX
    Explanations

    stands for definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vaccinate
    0.42
    скет
    0.41
     gently
    0.41
     trusty
    0.41
    ilmente
    0.40
     fuel
    0.40
     fuels
    0.40
     safe
    0.39
     lightly
    0.38
     pathogenic
    0.38
    POSITIVE LOGITS
     Databases
    0.45
    になる
    0.40
    意義
    0.38
     atrophy
    0.38
    ግብ
    0.38
    なくなる
    0.37
     Cochrane
    0.37
     at
    0.37
    大多数
    0.36
    पैकी
    0.36
    Act Density 0.000%

    No Known Activations