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

    Neuronpedia

    INDEX
    Explanations

    code snippet examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    די
    0.40
    轄
    0.39
     بنگالی
    0.37
    皈
    0.37
     منٹو
    0.37
    ེ
    0.37
    ὲ
    0.37
    ዞ
    0.37
    🤚
    0.37
     amphibians
    0.36
    POSITIVE LOGITS
    mr
    0.41
    образной
    0.37
     насы
    0.37
    mas
    0.37
    nc
    0.37
    ijken
    0.36
     как
    0.36
     veces
    0.36
     রাস্তায়
    0.35
     দেয়
    0.35
    Act Density 0.000%

    No Known Activations