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

    Neuronpedia

    INDEX
    Explanations

    retrace your steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    orpio
    0.39
     Trên
    0.38
    বিস্ত
    0.38
     générateur
    0.38
     مطالب
    0.37
     زخ
    0.37
    ối
    0.37
     플랫폼
    0.36
    搜尋
    0.36
     দোকানে
    0.35
    POSITIVE LOGITS
     ma
    0.42
    Opens
    0.41
    College
    0.40
    했고
    0.40
    LocalDate
    0.39
     ज़कात
    0.39
     sudoku
    0.39
     sit
    0.38
    Stone
    0.38
     Laughlin
    0.38
    Act Density 0.000%

    No Known Activations