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

    Neuronpedia

    INDEX
    Explanations

    inserting into or adding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出了
    0.47
    куси
    0.42
    icione
    0.40
     구
    0.40
    eteer
    0.40
    蕴
    0.40
     çık
    0.39
     Приступ
    0.39
     அட
    0.38
    тельности
    0.38
    POSITIVE LOGITS
     into
    1.12
    into
    1.00
     insertion
    0.99
    Into
    0.97
     vào
    0.96
     Into
    0.90
     inserting
    0.89
     इनटू
    0.87
     insertions
    0.87
     inser
    0.84
    Act Density 0.009%

    No Known Activations