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

    Neuronpedia

    INDEX
    Explanations

    Spanish "unos" and Vietnamese "chính"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    л
    1.47
    ется
    1.45
    ↵
    1.42
     eftersom
    1.40
     اﻷ
    1.38
     һәм
    1.36
     ปี
    1.35
    тре
    1.34
     등
    1.32
     וא
    1.31
    POSITIVE LOGITS
    م
    1.80
    이었
    1.77
    m
    1.76
    brows
    1.63
    กาย
    1.56
    ند
    1.55
    imiz
    1.55
    mib
    1.52
    ulence
    1.49
    대로
    1.49
    Act Density 0.001%

    No Known Activations