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

    Neuronpedia

    INDEX
    Explanations

    except

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    දී
    1.62
    ngày
    1.59
     berikutnya
    1.53
     aksi
    1.50
    popularity
    1.47
     swoje
    1.45
     hennes
    1.45
     legitimacy
    1.45
     наличии
    1.45
    अपनी
    1.43
    POSITIVE LOGITS
    з
    1.11
    ़
    1.09
     broadening
    1.02
    노
    1.02
    н
    1.01
    土
    0.97
    iced
    0.96
    ٰ
    0.96
     бюджета
    0.95
     пирами
    0.95
    Act Density 0.034%

    No Known Activations