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

    Neuronpedia

    INDEX
    Explanations

    corruption perception index

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    QUENCY
    0.41
    larında
    0.40
    میر
    0.39
     COUNTY
    0.38
    ISC
    0.38
    sf
    0.38
     Fernando
    0.37
     extensión
    0.37
     কালিক
    0.37
    乡村
    0.36
    POSITIVE LOGITS
     Perception
    0.45
     perceptions
    0.42
     sensing
    0.42
     gat
    0.41
     perception
    0.40
    ሯ
    0.40
    感知
    0.40
     om
    0.40
    퓨
    0.40
    uset
    0.39
    Act Density 0.006%

    No Known Activations