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

    Neuronpedia

    INDEX
    Explanations

    addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     doanh
    0.42
    лега
    0.41
    ケーション
    0.39
    نيه
    0.38
     ذریع
    0.38
    ေသ
    0.38
     instancia
    0.38
    ्‍य
    0.37
    ছা
    0.36
     اﻻ
    0.36
    POSITIVE LOGITS
    7
    0.45
    paired
    0.44
     Париж
    0.42
    ards
    0.42
    8
    0.40
    common
    0.40
    4
    0.39
    ⅝
    0.39
     Sunt
    0.39
    5
    0.39
    Act Density 0.001%

    No Known Activations