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

    Neuronpedia

    INDEX
    Explanations

    %

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.68
     faça
    0.50
    ไม่
    0.47
    ﻮ
    0.44
     получить
    0.41
    ﺮ
    0.40
     было
    0.39
     deseja
    0.39
     хотят
    0.39
    жды
    0.39
    POSITIVE LOGITS
    ين
    0.45
    ot
    0.36
    人々
    0.36
    蜚
    0.34
    ur
    0.34
     other
    0.34
    atot
    0.34
    涳
    0.34
    iin
    0.32
     Merkezi
    0.32
    Act Density 0.000%

    No Known Activations