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

    Neuronpedia

    INDEX
    Explanations

    start of numbered lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oğlu
    1.70
     tenders
    1.70
    /=
    1.70
    Only
    1.69
     protestors
    1.66
    大部分
    1.62
    o
    1.60
     protesters
    1.57
     doar
    1.57
    #{
    1.56
    POSITIVE LOGITS
    ﺔ
    1.92
    ﻴ
    1.71
    ﺒ
    1.66
    ﻲ
    1.59
    ﺪ
    1.58
     Synergy
    1.54
    ﻔ
    1.52
    ﻬ
    1.50
    ORY
    1.50
    ﺎ
    1.49
    Act Density 0.807%

    No Known Activations