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

    Neuronpedia

    INDEX
    Explanations

    write down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dificultades
    0.47
     sinuses
    0.46
    erçe
    0.43
     publicaciones
    0.42
     periodicals
    0.41
     Monsanto
    0.41
     Caja
    0.40
    葲
    0.40
     лікар
    0.40
     جع
    0.40
    POSITIVE LOGITS
     down
    0.55
    down
    0.50
    WRITE
    0.47
    write
    0.47
     onto
    0.45
    Write
    0.45
     xuống
    0.44
    list
    0.43
     write
    0.43
     verbatim
    0.42
    Act Density 0.029%

    No Known Activations