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

    Neuronpedia

    INDEX
    Explanations

    M&E systems design and implementation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lửa
    0.51
     belakang
    0.49
     phủ
    0.49
     Chất
    0.47
     każdego
    0.47
    θ
    0.47
     plików
    0.47
    ány
    0.47
     chất
    0.46
     yattha
    0.46
    POSITIVE LOGITS
    Peace
    0.49
    ديد
    0.48
    March
    0.47
    س
    0.47
    Ethiop
    0.47
    I
    0.46
    ٢
    0.45
    ﻫ
    0.45
    بغ
    0.45
    Gift
    0.44
    Act Density 0.001%

    No Known Activations