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

    Neuronpedia

    INDEX
    Explanations

    responsible care

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    3.56
    та
    3.16
    𝙲
    3.02
    yı
    2.97
    cı
    2.75
    ार्किक
    2.72
    ع
    2.72
    ಹ
    2.70
    Введите
    2.68
    璽
    2.67
    POSITIVE LOGITS
     ठहरा
    3.20
    أ
    2.96
    hete
    2.66
     ving
    2.57
    ंना
    2.37
    нтов
    2.33
    ृती
    2.29
    خوان
    2.25
     shutters
    2.25
    ジン
    2.25
    Act Density 0.034%

    No Known Activations